CN110135661A - A kind of the water process amount prediction technique and device of fired power generating unit desalted water station - Google Patents
A kind of the water process amount prediction technique and device of fired power generating unit desalted water station Download PDFInfo
- Publication number
- CN110135661A CN110135661A CN201910462217.7A CN201910462217A CN110135661A CN 110135661 A CN110135661 A CN 110135661A CN 201910462217 A CN201910462217 A CN 201910462217A CN 110135661 A CN110135661 A CN 110135661A
- Authority
- CN
- China
- Prior art keywords
- generating unit
- power generating
- fired power
- sample
- desalted water
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 465
- 238000000034 method Methods 0.000 title claims abstract description 212
- 230000008569 process Effects 0.000 title claims abstract description 162
- 238000010248 power generation Methods 0.000 claims abstract description 82
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 claims abstract description 45
- 229910052739 hydrogen Inorganic materials 0.000 claims abstract description 45
- 239000001257 hydrogen Substances 0.000 claims abstract description 45
- 239000013598 vector Substances 0.000 claims description 174
- 230000004927 fusion Effects 0.000 claims description 31
- 238000005070 sampling Methods 0.000 claims description 31
- 238000013528 artificial neural network Methods 0.000 claims description 30
- 230000000306 recurrent effect Effects 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 21
- 238000013136 deep learning model Methods 0.000 claims description 20
- 230000005619 thermoelectricity Effects 0.000 claims description 15
- 238000012163 sequencing technique Methods 0.000 claims description 14
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 11
- 229910052799 carbon Inorganic materials 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 11
- 238000001223 reverse osmosis Methods 0.000 claims description 11
- 238000000108 ultra-filtration Methods 0.000 claims description 11
- 238000005342 ion exchange Methods 0.000 claims description 9
- 239000002351 wastewater Substances 0.000 claims description 9
- 150000003839 salts Chemical class 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 4
- 230000005611 electricity Effects 0.000 claims description 3
- 230000015654 memory Effects 0.000 description 14
- 238000003860 storage Methods 0.000 description 9
- 238000010612 desalination reaction Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000005096 rolling process Methods 0.000 description 3
- 241001123248 Arma Species 0.000 description 2
- 206010006895 Cachexia Diseases 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 150000002500 ions Chemical class 0.000 description 2
- 208000016318 wasting Diseases 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 150000001450 anions Chemical class 0.000 description 1
- 150000001768 cations Chemical class 0.000 description 1
- 239000000084 colloidal system Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000004065 wastewater treatment Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Separation Using Semi-Permeable Membranes (AREA)
Abstract
This application provides a kind of water process amount prediction technique of fired power generating unit desalted water station and devices, wherein, this method comprises: obtaining desalted water station type, boiler type, the hydrogen generator station type of target fired power generating unit desalted water station, the duration that desalted water station puts into operation, fired power generating unit the power generation durations of multiple historical time sections, fired power generating unit the generated energy of each historical time section, fired power generating unit the estimated power generation duration of at least one future time section, fired power generating unit at least one future time section estimated generated energy；According to the above- mentioned information of acquisition, and the water process amount prediction model of fired power generating unit desalted water station trained in advance, target fired power generating unit desalted water station is obtained in the water process amount of each future time section.The water consumption that the application can be realized to fired power generating unit desalted water station in each period is predicted.
Description
Technical field
This application involves thermal power plant's administrative skill fields, at a kind of water of fired power generating unit desalted water station
Reason amount prediction technique and device.
Background technique
Demineralized water (desalted water) refers to using various water treatment technologies, removes suspended matter, colloid and inorganic
After the impurities in water such as cation, anion, obtained product water.Fired power generating unit demineralized water is mainly used for boiler feedwater.
Currently, fired power generating unit desalted water station is built according to the entire period of service maximum water consumption of fired power generating unit, but real process
In, the water consumption of demineralized water can cause Present Thermal Power machine in the different phase different from of the period of service of different fired power generating units
Group desalted water station the problems such as there are the water process wastings of resources；How the water process amount of the desalted water station of fired power generating unit is carried out pre-
It surveys, is current urgent problem to be solved.
Summary of the invention
In view of this, a kind of water process amount prediction for being designed to provide fired power generating unit desalted water station of the embodiment of the present application
Method and device can be realized the water consumption to fired power generating unit desalted water station in each period and predict.
In a first aspect, the embodiment of the present application provides a kind of water process amount prediction technique of fired power generating unit desalted water station, packet
It includes:
Desalted water station type, boiler type, the hydrogen generator station type of target fired power generating unit desalted water station are obtained, desalted water station is thrown
Enter the duration of operation, fired power generating unit is in the power generation durations of multiple historical time sections, fired power generating unit in each historical time section
Generated energy, fired power generating unit the estimated power generation duration of at least one future time section, fired power generating unit it is described at least one not
Carry out the estimated generated energy of period；
According to the desalted water station type, boiler type, hydrogen generator station type, the duration that desalted water station puts into operation, thermoelectricity
Unit is in the generated energy in each historical time section of power generation duration, fired power generating unit of multiple historical time sections, fired power generating unit
The estimated power generation duration of at least one future time section, fired power generating unit at least one future time section estimated power generation
Amount, and the water process amount prediction model of fired power generating unit desalted water station trained in advance, obtain the target fired power generating unit desalination
Water process amount of the water station in each future time section.
In a kind of optional embodiment, the water process amount prediction model of the fired power generating unit desalted water station includes depth
Practise model；
The deep learning model includes: Recognition with Recurrent Neural Network and Fusion Features network；
Using the following manner training deep learning model:
Obtain sample desalted water station type, boiler type, the hydrogen generator station type of multiple sample fired power generating unit desalted water stations, sample
The duration that this desalted water station puts into operation, power generation duration of the sample fired power generating unit in multiple sample historical time sections, sample thermoelectricity
Unit the generated energy of each sample historical time section, sample fired power generating unit desalted water station each sample historical time section reality
Border water process amount；
According to sample fired power generating unit in the power generation durations of multiple sample historical time sections, sample fired power generating unit in each sample
The generated energy of historical time section generates characteristic vector sequence according to the sequencing of sample historical time section；Sampling feature vectors
In sequence, including multiple first sample feature vectors；
According to sample desalted water station type, boiler type, the hydrogen generator station type of sample fired power generating unit desalted water station, sample is removed
The duration that salt water station puts into operation constitutes the second sampling feature vectors of each sample fired power generating unit desalted water station；
By sampling feature vectors sequence inputting into Recognition with Recurrent Neural Network, obtains and distinguish with each first sample feature vector
Corresponding median feature vector；
For each first sample feature vector, which is spelled with the second sampling feature vectors
It connects, forms sample corresponding with the first sample feature vector and splice vector；
The corresponding sample splicing vector of each first sample feature vector is input in Fusion Features network respectively, is obtained
Water process amount prediction result corresponding with the first sample feature vector；
It is special according to the corresponding water process amount prediction result of each first sample feature vector and each first sample
Levy the practical water process amount of the corresponding sample historical time section of vector, training Recognition with Recurrent Neural Network and Fusion Features network.
It is described to obtain the target fired power generating unit desalted water station in the water of future time section in a kind of optional embodiment
Treating capacity, comprising:
According to fired power generating unit in the power generation durations of multiple historical time sections, fired power generating unit in each historical time section
Generated energy, fired power generating unit are in the estimated power generation duration of at least one future time section, fired power generating unit at least one described future
The estimated generated energy of period generates feature vector according to the sequencing of each the historical time section and future time section
Sequence；Described eigenvector sequence includes multiple first eigenvectors；
According to the desalted water station type, boiler type, hydrogen generator station type of target fired power generating unit desalted water station, desalted water station is thrown
Enter the duration of operation, generates second feature vector；
By described eigenvector sequence inputting to Recognition with Recurrent Neural Network, median feature vector is obtained；
Each median feature vector is spliced with the second feature vector respectively, is generated and each intermediate spy
The corresponding splicing vector of vector is levied, and each splicing vector is input in the Fusion Features network, obtains institute
Target fired power generating unit desalted water station is stated in the water process amount of each future time section.
In a kind of optional embodiment, this method further include:
According to the target fired power generating unit desalted water station in the water process amount of future time section, the target thermal motor is determined
Ultrafiltration apparatus, active carbon filtration system in group desalted water station, reverse osmosis treatment system and ion-exchange treatment system are described
The runing time and operation power of future time section.
In a kind of optional embodiment, this method further include:
According to the target fired power generating unit desalted water station in the water process amount of future time section, discharge wastewater flow rate is determined.
Second aspect, the embodiment of the present application also provide a kind of water process amount prediction meanss of fired power generating unit desalted water station, packet
It includes:
Module is obtained, for obtaining the desalted water station type, boiler type, hydrogen generator station class of target fired power generating unit desalted water station
Type, the duration that desalted water station puts into operation, fired power generating unit is in the power generation durations of multiple historical time sections, fired power generating unit in each institute
The generated energy of historical time section, fired power generating unit are stated in the estimated power generation duration of at least one future time section, fired power generating unit in institute
State the estimated generated energy of at least one future time section；
Prediction module, for according to the desalted water station type, boiler type, hydrogen generator station type, desalted water station investment fortune
Capable duration, fired power generating unit the power generation durations of multiple historical time sections, fired power generating unit each historical time section hair
Electricity, fired power generating unit the estimated power generation duration of at least one future time section, fired power generating unit it is described at least one it is following when
Between section estimated generated energy, and the water process amount prediction model of fired power generating unit desalted water station trained in advance obtains the mesh
Fired power generating unit desalted water station is marked in the water process amount of each future time section.
In a kind of optional embodiment, the water process amount prediction model of the fired power generating unit desalted water station includes depth
Practise model；
The deep learning model includes: Recognition with Recurrent Neural Network and Fusion Features network；
Further include: model training module, for using the following manner training deep learning model:
Obtain sample desalted water station type, boiler type, the hydrogen generator station type of multiple sample fired power generating unit desalted water stations, sample
The duration that this desalted water station puts into operation, power generation duration of the sample fired power generating unit in multiple sample historical time sections, sample thermoelectricity
Unit the generated energy of each sample historical time section, sample fired power generating unit desalted water station each sample historical time section reality
Border water process amount；
According to sample fired power generating unit in the power generation durations of multiple sample historical time sections, sample fired power generating unit in each sample
The generated energy of historical time section generates characteristic vector sequence according to the sequencing of sample historical time section；Sampling feature vectors
In sequence, including multiple first sample feature vectors；
According to sample desalted water station type, boiler type, the hydrogen generator station type of sample fired power generating unit desalted water station, sample is removed
The duration that salt water station puts into operation constitutes the second sampling feature vectors of each sample fired power generating unit desalted water station；
By sampling feature vectors sequence inputting into Recognition with Recurrent Neural Network, obtains and distinguish with each first sample feature vector
Corresponding median feature vector；
For each first sample feature vector, which is spelled with the second sampling feature vectors
It connects, forms sample corresponding with the first sample feature vector and splice vector；
The corresponding sample splicing vector of each first sample feature vector is input in Fusion Features network respectively, is obtained
Water process amount prediction result corresponding with the first sample feature vector；
It is special according to the corresponding water process amount prediction result of each first sample feature vector and each first sample
Levy the practical water process amount of the corresponding sample historical time section of vector, training Recognition with Recurrent Neural Network and Fusion Features network.
In a kind of optional embodiment, the prediction module, for obtaining the target thermal motor using following manner
Water process amount of the group desalted water station in future time section:
According to fired power generating unit in the power generation durations of multiple historical time sections, fired power generating unit in each historical time section
Generated energy, fired power generating unit are in the estimated power generation duration of at least one future time section, fired power generating unit at least one described future
The estimated generated energy of period generates feature vector according to the sequencing of each the historical time section and future time section
Sequence；Described eigenvector sequence includes multiple first eigenvectors；
According to the desalted water station type, boiler type, hydrogen generator station type of target fired power generating unit desalted water station, desalted water station is thrown
Enter the duration of operation, generates second feature vector；
By described eigenvector sequence inputting to Recognition with Recurrent Neural Network, median feature vector is obtained；
Each median feature vector is spliced with the second feature vector respectively, is generated and each intermediate spy
The corresponding splicing vector of vector is levied, and each splicing vector is input in the Fusion Features network, obtains institute
Target fired power generating unit desalted water station is stated in the water process amount of each future time section.
In a kind of optional embodiment, the device further include:
First determining module, for according to the target fired power generating unit desalted water station future time section water process amount,
Determine ultrafiltration apparatus, active carbon filtration system, reverse osmosis treatment system and the ion in the target fired power generating unit desalted water station
Processing system is exchanged in the runing time of the future time section and operation power.
In a kind of optional embodiment, the device further include:
Second determining module, for according to the target fired power generating unit desalted water station future time section water process amount,
Determine discharge wastewater flow rate.
The third aspect, the embodiment of the present application also provide a kind of electronic equipment, comprising: processor, memory and bus, it is described
Memory is stored with the executable machine readable instructions of the processor, when electronic equipment operation, the processor with it is described
By bus communication between memory, the machine readable instructions executed when being executed by the processor it is above-mentioned in a first aspect, or
Step in any possible embodiment of first aspect.
Fourth aspect, the embodiment of the present application also provide a kind of computer readable storage medium, the computer-readable storage medium
Computer program is stored in matter, which executes above-mentioned in a first aspect, or first aspect times when being run by processor
A kind of step in possible embodiment.
Desalted water station type, the boiler type, hydrogen manufacturing that the embodiment of the present application passes through acquisition target fired power generating unit desalted water station
It stands type, the duration that desalted water station puts into operation, fired power generating unit is in the power generation durations of multiple historical time sections, fired power generating unit each
The generated energy of a historical time section, fired power generating unit at least one future time section estimated power generation duration, fired power generating unit
In the estimated generated energy of at least one future time section；And according to the relevant information of acquisition, and thermoelectricity trained in advance
The water process amount prediction model of unit desalted water station is realized to target fired power generating unit desalted water station in each future time section
Water process amount prediction.To enable the above objects, features, and advantages of the application to be clearer and more comprehensible, preferable implementation is cited below particularly
Example, and cooperate appended attached drawing, it is described in detail below.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows a kind of water process amount prediction technique of fired power generating unit desalted water station provided by the embodiment of the present application
Flow chart；
Fig. 2 shows in the water process amount prediction technique of fired power generating unit desalted water station provided by the embodiment of the present application, instruct
Practice the flow chart of the specific method of water process amount prediction model；
Fig. 3 is shown in the water process amount prediction technique of fired power generating unit desalted water station provided by the embodiment of the present application, is obtained
Take the target fired power generating unit desalted water station in the flow chart of the specific method of the water process amount of future time section；
Fig. 4 shows a kind of water process amount prediction meanss of fired power generating unit desalted water station provided by the embodiment of the present application
Schematic diagram；
Fig. 5 shows the schematic diagram of a kind of electronic equipment provided by the embodiment of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
Middle attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
It is some embodiments of the present application, instead of all the embodiments.The application being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, below to the application's provided in the accompanying drawings
The detailed description of embodiment is not intended to limit claimed scope of the present application, but is merely representative of the selected reality of the application
Apply example.Based on embodiments herein, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall in the protection scope of this application.
Thermal power plant is usually divided into more phase engineerings and builds respectively during construction.Each issue of engineering can build a fixed number
The fired power generating unit of amount, and the later engineering of building time, when building, the fired power generating unit built up has been put into operation.Desalination
Boiler feedwater of the water as fired power generating unit is essential raw material of the fired power generating unit in power generation process.Desalted water station is made
For the production system of demineralized water, usually needed according to the maximum that all fired power generating units of more phase engineerings of thermal power plant put into effect
Water is built, but in real process, and the water consumption of demineralized water can have in the different service stages of the period of service of fired power generating unit
It is distinguished, the problems such as causing Present Thermal Power unit desalted water station there are the water process wastings of resources.Therefore, one kind can be with more high-precision
The mode predicted the water process amount of desalted water station is spent, current urgent problem to be solved is become.
Based on the studies above, this application provides a kind of water process amount prediction technique of fired power generating unit desalted water station and dresses
It sets, influences two characteristic values under feature in multiple water process by obtaining target fired power generating unit desalted water station, and by the spy of acquisition
Value indicative is input in the water process amount prediction model of fired power generating unit desalted water station trained in advance, obtains target fired power generating unit desalination
Water station future time section water process amount, to instruct the water treatment work of fired power generating unit desalted water station.
For defect present in above scheme, be inventor being obtained after practicing and carefully studying as a result,
Therefore, the discovery procedure of the above problem and the solution that hereinafter the application is proposed regarding to the issue above all should be
The contribution that inventor makes the application during the application.
Below in conjunction with attached drawing in the application, the technical solution in the application is clearly and completely described, it is clear that
Described embodiments are only a part of embodiments of the present application, instead of all the embodiments.Usually retouched in attached drawing here
The component for the application for stating and showing can be arranged and be designed with a variety of different configurations.Therefore, below to mentioning in the accompanying drawings
The detailed description of the embodiments herein of confession is not intended to limit claimed scope of the present application, but is merely representative of this
The selected embodiment of application.Based on embodiments herein, those skilled in the art are in the premise for not making creative work
Under every other embodiment obtained, shall fall in the protection scope of this application.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
For convenient for understanding the present embodiment, first to a kind of fired power generating unit demineralized water disclosed in the embodiment of the present application
The water process amount prediction technique stood describes in detail, the water process of fired power generating unit desalted water station provided by the embodiment of the present application
The executing subject of amount prediction technique is typically the computer equipment of operational capability.
Embodiment one
It is shown in Figure 1, for the water process amount prediction technique for the fired power generating unit desalted water station that the embodiment of the present application one provides
Flow chart, the method includes the steps S101~S102, in which:
S101: desalted water station type, boiler type, the hydrogen generator station type of target fired power generating unit desalted water station, desalination are obtained
The duration that water station puts into operation, fired power generating unit is in the power generation durations of multiple historical time sections, fired power generating unit in each history
The generated energy of period, fired power generating unit the estimated power generation duration of at least one future time section, fired power generating unit it is described at least
The estimated generated energy of one future time section.
In specific implementation, to there are many influence factors of desalted water station, such as operation power, the thermal motor of fired power generating unit
In group in the type, fired power generating unit of boiler when the power generation of the type of hydrogen generator station, the duration that desalted water station puts into effect, fired power generating unit
Long, fired power generating unit generated energy etc., in addition, further including ultrafiltration apparatus in desalted water station, active carbon filtration system, reverse osmosis place
The operation conditions of reason system and ion-exchange treatment system, also can the water process amount to desalted water station affect.This
Apply in embodiment, is handed in view of ultrafiltration apparatus, active carbon filtration system in desalted water station, reverse osmosis treatment system and ion
In the case where changing processing system normal work, the application uses desalted water station type, boiler type, hydrogen generator station type, demineralized water
The duration that station is put into operation, fired power generating unit in the power generation durations of multiple historical time sections, fired power generating unit in each history
The generated energy of period, fired power generating unit the estimated power generation duration of at least one future time section, fired power generating unit it is described at least
The estimated generated energy of one future time section predicts the water process amount of fired power generating unit desalted water station.
Here, the quantity of historical time section is the time put into operation according to desalted water station and each historical time section
Duration determine.
For example, if using fired power generating unit desalted water station provided by the embodiments of the present application water process amount prediction technique, prediction
The water process amount using the desalted water station of certain time in following certain time has been put into, if predicted time is January 1 in 2018
Day, (predicted time was as predicted using the water process amount prediction technique of fired power generating unit desalted water station provided by the embodiments of the present application
Time of the target fired power generating unit desalted water station in the water process amount of at least one future time section), historical time section when a length of 2
A month, the time that desalted water station puts into operation was on January 1st, 2017, then corresponding historical time section has 6, is respectively as follows:
On 2 29th, 1 on the 1st January in 2017；
On April 30, -2017 years on the 1st March in 2017；
On June 30, -2017 years on the 1st May in 2017；
August 31st -2017 years on the 1st July in 2017；
- 2017 years on the 1st October 31 of September in 2017；
On December 31, -2017 years on the 1st November in 2017.
Corresponding, the duration of each future time section is also 2 months, in the examples described above, when being predicted, energy
Enough obtain on January 1st, 2018 after future time section water process amount.
For example, the future time section determined includes:
On 2 29th, 1 on the 1st January in 2018；
On April 30, -2018 years on the 1st March in 2018.
If prediction is not put into using the water process amount prediction technique of fired power generating unit desalted water station provided by the embodiments of the present application
The desalted water station used corresponds to historical time section then in the water process amount of following certain time as sky.
Each future time section is at least one the future time section of desalted water station after coming into operation.
For example, predicted time is on January 1st, 2018, desalted water station plan is come into operation on January 1st, 2019, then when following
Between section may include:
On 2 29th, 1 on the 1st January in 20179；
On April 30, -2019 years on the 1st March in 2019；
On June 30, -2019 years on the 1st May in 2019；
August 31st -2019 years on the 1st July in 2019.
Specifically, it can determine that target fired power generating unit desalted water station influences feature in each water process amount using following manner
Under characteristic value:
(1) desalted water station type, boiler type, hydrogen generator station type can directly be read from the management system of fired power generating unit
It takes.
Wherein, fired power generating unit management system is the control system to generate electricity for managing fired power generating unit.
(2) duration that desalted water station puts into operation: the time that can be put into operation by desalted water station, and when prediction
Between, determine the duration that desalted water station puts into operation；Or after being put into operation by desalted water station, in the work of each historical time section
The duration that desalted water station puts into operation is determined as duration.
(3) generated energy of the fired power generating unit in each historical time section: can also be directly from the management system of fired power generating unit
It is read in system.
(4) fired power generating unit the estimated power generation duration of at least one future time section, fired power generating unit it is described at least one
The estimated generated energy of future time section determines according to actual power generation needs, or from the relevant information of thermal power plant's generation schedule
Middle reading.
S102: according to the desalted water station type, boiler type, hydrogen generator station type, the duration that desalted water station puts into operation,
Fired power generating unit the power generation durations of multiple historical time sections, fired power generating unit each historical time section generated energy, thermoelectricity
Unit is in the estimated power generation duration of at least one future time section, fired power generating unit in the estimated of at least one future time section
Generated energy, and the water process amount prediction model of fired power generating unit desalted water station trained in advance, obtain the target fired power generating unit
Water process amount of the desalted water station in each future time section.
In specific implementation, the water process amount prediction model of fired power generating unit desalted water station, may include: logistic regression mould
Type, autoregression model, moving average model(MA model), ARMA model, integrating rolling average autoregression model, broad sense, oneself returns
Return Conditional heterosedasticity model, any one in deep learning model.
For different types of water process amount prediction model, there can be different training methods.
A: including the case where deep learning model for the water process amount prediction model of the fired power generating unit desalted water station, should
Deep learning model includes: Recognition with Recurrent Neural Network and Fusion Features network.
Shown in Figure 2, the embodiment of the present application provides a kind of concrete mode of trained water process amount prediction model, comprising:
S201: sample desalted water station type, boiler type, the hydrogen generator station class of multiple sample fired power generating unit desalted water stations are obtained
Type, the duration that sample desalted water station puts into operation, power generation duration of the sample fired power generating unit in multiple sample historical time sections, sample
Fired power generating unit is in the generated energy of each sample historical time section, sample fired power generating unit desalted water station in each sample historical time section
Practical water process amount.
S202: according to sample fired power generating unit in the power generation durations of multiple sample historical time sections, sample fired power generating unit each
The generated energy of a sample historical time section generates characteristic vector sequence according to the sequencing of sample historical time section；Sample is special
It levies in sequence vector, including multiple first sample feature vectors.
Wherein, the corresponding sample historical time section of each first sample feature vector, and the number of sample historical time section
Amount, in following S102, historical time section is consistent with the total quantity of future time section.
Herein, if sample fired power generating unit is identical as the type of target fired power generating unit, can by with sample fired power generating unit
The power generation durations of multiple sample historical time sections, sample fired power generating unit each sample historical time section generated energy structure
At sampling feature vectors sequence.
In another embodiment, if sample fired power generating unit is different from the type of target fired power generating unit, in sampling feature vectors
It can also include other relevant informations of generating set, such as the power generation function in the power generation of each sample historical time section in sequence
Rate etc..
S203: according to sample desalted water station type, boiler type, the hydrogen generator station type of sample fired power generating unit desalted water station,
The duration that sample desalted water station puts into operation constitutes the second sampling feature vectors of each sample fired power generating unit desalted water station.
S204: by sampling feature vectors sequence inputting into Recognition with Recurrent Neural Network, obtain with each first sample feature to
Measure corresponding median feature vector.
S205: it is directed to each first sample feature vector, by the first sample feature vector and the second sampling feature vectors
Spliced, forms sample corresponding with the first sample feature vector and splice vector.
S206: the corresponding sample splicing vector of each first sample feature vector is input to Fusion Features network respectively
In, obtain water process amount prediction result corresponding with the first sample feature vector.
S207: according to the corresponding water process amount prediction result of each first sample feature vector and each first
The practical water process amount of the corresponding sample historical time section of sampling feature vectors, training Recognition with Recurrent Neural Network and Fusion Features
Network.
Herein, according to the corresponding water process amount prediction result of each first sample feature vector and each first
The practical water process amount of the corresponding sample historical time section of sampling feature vectors, training Recognition with Recurrent Neural Network and Fusion Features
Network is for each first sample feature vector, according to the corresponding output strength prediction result of the first sample feature vector
With the practical water process of corresponding sample historical time section as a result, obtaining the intersection entropy loss of deep learning model, and according to depth
The intersection entropy loss of learning model adjusts the parameter of Recognition with Recurrent Neural Network and Fusion Features network, finally to recycle nerve net
Network and Fusion Features network are the water process amount prediction result that each sample historical time section is estimated, with each sample historical time
Difference between the corresponding practical water process amount of section, is less than preset difference threshold.
After training obtains water process amount prediction model, it will be able to obtain target thermoelectricity based on the water process amount prediction model
Water process amount of the unit at least one future time section.
Specifically, shown in Figure 3, the embodiment of the present application also provides a kind of water process amount in fired power generating unit desalted water station
In the case that prediction model includes deep learning model, the target fired power generating unit desalted water station is obtained in the water of future time section
The concrete mode for the treatment of capacity, comprising:
S301: according to fired power generating unit in the power generation durations of multiple historical time sections, fired power generating unit in each history
Between the generated energy of section, fired power generating unit in the estimated power generation duration of at least one future time section, fired power generating unit described at least one
The estimated generated energy of a future time section generates characteristic vector sequence according to the sequencing of each historical time section；Institute
Stating characteristic vector sequence includes multiple first eigenvectors.
It is herein, identical as the quantity of sample historical time section due to the sum of historical time section and the quantity of future time section,
In the characteristic vector sequence constituted, the quantity of first eigenvector is also identical with the quantity of first sample feature vector.Wherein,
First eigenvector is corresponded with historical time section and future time section.
That is, if the desalted water station of target fired power generating unit put into operation when it is 6 months a length of, historical time section and it is following when
Between the duration of section be 2 months, and the quantity of historical time section and future time section and have 10, then corresponding historical time section
Quantity be 3, the quantity of future time section is 7.It is obtained to be, desalted water station in the 7 following future time sections,
Water process amount in each future time section.
If the desalted water station of target fired power generating unit does not put into operation also, the duration of historical time section and future time section is
2 months, and the quantity of historical time section and future time section and have 10, then the quantity of corresponding historical time section is 0, not
The quantity for carrying out the period is 10.It is obtained to be, desalted water station future put into effect after 20 future time sections in,
Water process amount in each future time section.
S302: according to desalted water station type, boiler type, hydrogen generator station type, the duration that desalted water station puts into operation is generated
Second feature vector；
S303: by described eigenvector sequence inputting to Recognition with Recurrent Neural Network, median feature vector is obtained；
S304: each median feature vector is spliced with the second feature vector respectively, is generated and each
The corresponding splicing vector of median feature vector, and each splicing vector is input in the Fusion Features network,
The target fired power generating unit desalted water station is obtained in the water process amount of each future time section.
B: the water process amount prediction model for the fired power generating unit desalted water station includes: Logic Regression Models, autoregression
Model, moving average model(MA model), ARMA model, to integrate rolling average autoregression model, broad sense autoregressive conditions different
In Tobin's mean variance model any one the case where, it is shown in Figure 4 can using following manner training water process amount prediction model:
Obtain sample desalted water station type, boiler type, the hydrogen generator station type of multiple sample fired power generating unit desalted water stations, sample
The duration that this desalted water station puts into operation, power generation duration of the sample fired power generating unit in multiple sample historical time sections, sample thermoelectricity
Unit the generated energy of each sample historical time section, sample fired power generating unit desalted water station each sample historical time section reality
Border water process amount.
It is right according to sample desalted water station type, boiler type, the hydrogen generator station type of multiple sample fired power generating unit desalted water stations
Each sample fired power generating unit desalted water station is classified.
For each classification, using each sample fired power generating unit desalted water station in the classification as target fired power generating unit desalination
Water station, power generation duration, sample fired power generating unit according to each target fired power generating unit desalted water station in multiple sample historical time sections
The generated energy of each sample historical time section, sample fired power generating unit desalted water station each sample historical time section practical water
Treating capacity, training basic forecast model corresponding with the classification, obtains water process amount prediction model corresponding with the classification.
Specifically, as basic forecast model logic regression model, autoregression model, moving average model(MA model), autoregression move
Dynamic averaging model integrates rolling average autoregression model, any one in EC GARCH.
Basic forecast model can be trained using following manner:
Power generation duration, sample fired power generating unit with each target fired power generating unit desalted water station in multiple sample historical time sections
Each sample historical time section generated energy as independent variable matrix, gone through with sample fired power generating unit desalted water station in each sample
The practical water process amount of history period is as dependent variable matrix, to the ginseng of each independent variable and dependent variable in basic forecast model
Matrix number is solved, and the parameter of each independent variable and the parameter of dependent variable are obtained, and finally obtains water process amount prediction model.
When being predicted using water process amount of this kind of water process amount prediction model to target fired power generating unit desalted water station,
Following manner can be used:
According to the desalted water station type, boiler type, hydrogen generator station type of target fired power generating unit desalted water station, the determining and mesh
Mark the corresponding water process amount prediction model of fired power generating unit desalted water station.
By target fired power generating unit desalted water station fired power generating unit in the power generation durations of multiple historical time sections, fired power generating unit each
The generated energy of a historical time section, fired power generating unit at least one future time section estimated power generation duration, fired power generating unit
In value of the estimated generated energy as independent variable of at least one future time section, it is input in water process amount prediction model,
Obtain water process amount corresponding with each future time section.
In addition, in another embodiment of the application, in the water process amount prediction technique of provided motor group desalted water station, also
Include:
S103: according to the target fired power generating unit desalted water station in the water process amount of future time section, the target is determined
Ultrafiltration apparatus, active carbon filtration system in fired power generating unit desalted water station, reverse osmosis treatment system and ion-exchange treatment system
In the runing time and operation power of the future time section.
Herein, the ultrafiltration in the water process amount of target fired power generating unit desalted water station and target fired power generating unit desalted water station fills
It sets, active carbon filtration system, has between reverse osmosis treatment system and the runing time and operation power of ion-exchange treatment system
There are mapping relations.
Determining target fired power generating unit desalted water station after the water process amount of future time section, it will be able to according to the mapping
Relationship, determines ultrafiltration apparatus in the target fired power generating unit desalted water station, active carbon filtration system, reverse osmosis treatment system and
Runing time and operation power of the ion-exchange treatment system in the future time section.
In addition, in another embodiment of the application, in the water process amount prediction technique of provided motor group desalted water station, also
Include:
S104: according to the target fired power generating unit desalted water station in the water process amount of future time section, discharge waste water is determined
Amount.
Herein, there are mapping relations, true between the water process amount and waste water discharge rate of target fired power generating unit desalted water station
Target fired power generating unit desalted water station has been determined after the water process amount of future time section, it will be able to according to the mapping relations, the row of determination
Wastewater flow rate out, to instruct the related work of waste water treatment system.
In addition, in another embodiment of the application, in the water process amount prediction technique of provided motor group desalted water station, also
Include: the water process amount based on target fired power generating unit desalted water station in each future time section, deploys target fired power generating unit
The water process resource of desalted water station.
Desalted water station type, the boiler type, hydrogen manufacturing that the embodiment of the present application passes through acquisition target fired power generating unit desalted water station
It stands type, the duration that desalted water station puts into operation, fired power generating unit is in the power generation durations of multiple historical time sections, fired power generating unit each
The generated energy of a historical time section, fired power generating unit at least one future time section estimated power generation duration, fired power generating unit
In the estimated generated energy of at least one future time section；And according to the relevant information of acquisition, and thermoelectricity trained in advance
The water process amount prediction model of unit desalted water station is realized to target fired power generating unit desalted water station in each future time section
Water process amount prediction.
Based on the same inventive concept, it is additionally provided in the embodiment of the present application pre- with the water process amount of fired power generating unit desalted water station
The water process amount prediction meanss of the corresponding fired power generating unit desalted water station of survey method, since the device solution in the embodiment of the present application is asked
The principle of topic is similar to the water process amount prediction technique of the above-mentioned fired power generating unit desalted water station of the embodiment of the present application, therefore the reality of device
The implementation for the method for may refer to is applied, overlaps will not be repeated.
Embodiment two
Referring to shown in Fig. 4, for a kind of water process amount prediction for fired power generating unit desalted water station that the embodiment of the present application two provides
The schematic diagram of device, described device include: to obtain module 41 and prediction module 42；Wherein,
Module 41 is obtained, for obtaining desalted water station type, the boiler type, hydrogen generator station of target fired power generating unit desalted water station
Type, the duration that desalted water station puts into operation, fired power generating unit is in the power generation durations of multiple historical time sections, fired power generating unit each
The generated energy of the historical time section, fired power generating unit exist in estimated power generation duration, the fired power generating unit of at least one future time section
The estimated generated energy of at least one future time section；
Prediction module 42, for according to the desalted water station type, boiler type, hydrogen generator station type, desalted water station investment
The duration of operation, fired power generating unit is in the power generation durations of multiple historical time sections, fired power generating unit in each historical time section
Generated energy, fired power generating unit are in the estimated power generation duration of at least one future time section, fired power generating unit at least one described future
The estimated generated energy of period, and the water process amount prediction model of fired power generating unit desalted water station trained in advance, described in acquisition
Water process amount of the target fired power generating unit desalted water station in each future time section.
Desalted water station type, the boiler type, hydrogen manufacturing that the embodiment of the present application passes through acquisition target fired power generating unit desalted water station
It stands type, the duration that desalted water station puts into operation, fired power generating unit is in the power generation durations of multiple historical time sections, fired power generating unit each
The generated energy of a historical time section, fired power generating unit at least one future time section estimated power generation duration, fired power generating unit
In the estimated generated energy of at least one future time section；And according to the relevant information of acquisition, and thermoelectricity trained in advance
The water process amount prediction model of unit desalted water station is realized to target fired power generating unit desalted water station in each future time section
Water process amount prediction.
In a kind of possible embodiment, the water process amount prediction model of the fired power generating unit desalted water station includes depth
Practise model；
The deep learning model includes: Recognition with Recurrent Neural Network and Fusion Features network；
Further include: model training module 43, for using the following manner training deep learning model:
Obtain sample desalted water station type, boiler type, the hydrogen generator station type of multiple sample fired power generating unit desalted water stations, sample
The duration that this desalted water station puts into operation, power generation duration of the sample fired power generating unit in multiple sample historical time sections, sample thermoelectricity
Unit the generated energy of each sample historical time section, sample fired power generating unit desalted water station each sample historical time section reality
Border water process amount；
According to sample fired power generating unit in the power generation durations of multiple sample historical time sections, sample fired power generating unit in each sample
The generated energy of historical time section generates characteristic vector sequence according to the sequencing of sample historical time section；Sampling feature vectors
In sequence, including multiple first sample feature vectors；
According to sample desalted water station type, boiler type, the hydrogen generator station type of sample fired power generating unit desalted water station, sample is removed
The duration that salt water station puts into operation constitutes the second sampling feature vectors of each sample fired power generating unit desalted water station；
By sampling feature vectors sequence inputting into Recognition with Recurrent Neural Network, obtains and distinguish with each first sample feature vector
Corresponding median feature vector；
For each first sample feature vector, which is spelled with the second sampling feature vectors
It connects, forms sample corresponding with the first sample feature vector and splice vector；
The corresponding sample splicing vector of each first sample feature vector is input in Fusion Features network respectively, is obtained
Water process amount prediction result corresponding with the first sample feature vector；
It is special according to the corresponding water process amount prediction result of each first sample feature vector and each first sample
Levy the practical water process amount of the corresponding sample historical time section of vector, training Recognition with Recurrent Neural Network and Fusion Features network.
In a kind of possible embodiment, the prediction module 42, for obtaining the target thermoelectricity using following manner
Water process amount of the unit desalted water station in future time section:
According to fired power generating unit in the power generation durations of multiple historical time sections, fired power generating unit in each historical time section
Generated energy, fired power generating unit are in the estimated power generation duration of at least one future time section, fired power generating unit at least one described future
The estimated generated energy of period generates feature vector according to the sequencing of each the historical time section and future time section
Sequence；Described eigenvector sequence includes multiple first eigenvectors；
According to the desalted water station type, boiler type, hydrogen generator station type of target fired power generating unit desalted water station, desalted water station is thrown
Enter the duration of operation, generates second feature vector；
By described eigenvector sequence inputting to Recognition with Recurrent Neural Network, median feature vector is obtained；
Each median feature vector is spliced with the second feature vector respectively, is generated and each intermediate spy
The corresponding splicing vector of vector is levied, and each splicing vector is input in the Fusion Features network, obtains institute
Target fired power generating unit desalted water station is stated in the water process amount of each future time section.
In a kind of possible embodiment, the device further include: the first determining module 44, for according to the target thermoelectricity
Unit desalted water station in the water process amount of future time section, determine ultrafiltration apparatus in the target fired power generating unit desalted water station,
Active carbon filtration system, reverse osmosis treatment system and ion-exchange treatment system the future time section runing time and
Run power.
In a kind of possible embodiment, the device further include:
Second determining module 45, for according to the target fired power generating unit desalted water station future time section water process
Amount determines discharge wastewater flow rate.
Description about the interaction flow between the process flow and each module of each module in device is referred to
The related description in embodiment of the method is stated, I will not elaborate.
Embodiment three
500 structural schematic diagram of computer equipment of offer, comprising:
Processor 51, memory 52 and bus 53；Memory 52 is executed instruction for storing, including memory 521 and outside
Memory 522；Here memory 521 is also referred to as built-in storage, for temporarily storing the operational data in processor 51, and with it is hard
The data that the external memories such as disk 522 exchange, processor 51 carry out data exchange by memory 521 and external memory 522, when
When the computer equipment 500 is run, communicated between the processor 51 and the memory 52 by bus 53, so that described
Processor 61 is executed in User space to give an order:
Desalted water station type, boiler type, the hydrogen generator station type of target fired power generating unit desalted water station are obtained, desalted water station is thrown
Enter the duration of operation, fired power generating unit is in the power generation durations of multiple historical time sections, fired power generating unit in each historical time section
Generated energy, fired power generating unit the estimated power generation duration of at least one future time section, fired power generating unit it is described at least one not
Carry out the estimated generated energy of period；
According to the desalted water station type, boiler type, hydrogen generator station type, the duration that desalted water station puts into operation, thermoelectricity
Unit is in the generated energy in each historical time section of power generation duration, fired power generating unit of multiple historical time sections, fired power generating unit
The estimated power generation duration of at least one future time section, fired power generating unit at least one future time section estimated power generation
Amount, and the water process amount prediction model of fired power generating unit desalted water station trained in advance, obtain the target fired power generating unit desalination
Water process amount of the water station in each future time section.
In a kind of possible embodiment, in the instruction that processor 51 executes, at the water of the fired power generating unit desalted water station
Reason amount prediction model includes deep learning model；
The deep learning model includes: Recognition with Recurrent Neural Network and Fusion Features network；
Using the following manner training deep learning model:
Obtain sample desalted water station type, boiler type, the hydrogen generator station type of multiple sample fired power generating unit desalted water stations, sample
The duration that this desalted water station puts into operation, power generation duration of the sample fired power generating unit in multiple sample historical time sections, sample thermoelectricity
Unit the generated energy of each sample historical time section, sample fired power generating unit desalted water station each sample historical time section reality
Border water process amount；
According to sample fired power generating unit in the power generation durations of multiple sample historical time sections, sample fired power generating unit in each sample
The generated energy of historical time section generates characteristic vector sequence according to the sequencing of sample historical time section；Sampling feature vectors
In sequence, including multiple first sample feature vectors；
According to sample desalted water station type, boiler type, the hydrogen generator station type of sample fired power generating unit desalted water station, sample is removed
The duration that salt water station puts into operation constitutes the second sampling feature vectors of each sample fired power generating unit desalted water station；
By sampling feature vectors sequence inputting into Recognition with Recurrent Neural Network, obtains and distinguish with each first sample feature vector
Corresponding median feature vector；
For each first sample feature vector, which is spelled with the second sampling feature vectors
It connects, forms sample corresponding with the first sample feature vector and splice vector；
The corresponding sample splicing vector of each first sample feature vector is input in Fusion Features network respectively, is obtained
Water process amount prediction result corresponding with the first sample feature vector；
It is special according to the corresponding water process amount prediction result of each first sample feature vector and each first sample
Levy the practical water process amount of the corresponding sample historical time section of vector, training Recognition with Recurrent Neural Network and Fusion Features network.
It is described to obtain the target fired power generating unit and remove in the instruction that processor 51 executes in a kind of possible embodiment
Water process amount of the salt water station in future time section, comprising:
According to fired power generating unit in the power generation durations of multiple historical time sections, fired power generating unit in each historical time section
Generated energy, fired power generating unit are in the estimated power generation duration of at least one future time section, fired power generating unit at least one described future
The estimated generated energy of period generates feature vector according to the sequencing of each the historical time section and future time section
Sequence；Described eigenvector sequence includes multiple first eigenvectors；
According to the desalted water station type, boiler type, hydrogen generator station type of target fired power generating unit desalted water station, desalted water station is thrown
Enter the duration of operation, generates second feature vector；
By described eigenvector sequence inputting to Recognition with Recurrent Neural Network, median feature vector is obtained；
Each median feature vector is spliced with the second feature vector respectively, is generated and each intermediate spy
The corresponding splicing vector of vector is levied, and each splicing vector is input in the Fusion Features network, obtains institute
Target fired power generating unit desalted water station is stated in the water process amount of each future time section.
In a kind of possible embodiment, in the instruction that processor 51 executes, this method further include:
According to the target fired power generating unit desalted water station in the water process amount of future time section, the target thermal motor is determined
Ultrafiltration apparatus, active carbon filtration system in group desalted water station, reverse osmosis treatment system and ion-exchange treatment system are described
The runing time and operation power of future time section.
In a kind of possible embodiment, in the instruction that processor 51 executes, this method further include:
According to the target fired power generating unit desalted water station in the water process amount of future time section, discharge wastewater flow rate is determined.
In addition, the embodiment of the present application also provides a kind of computer readable storage medium, on the computer readable storage medium
It is stored with computer program, fired power generating unit described in above method embodiment is executed when which is run by processor
The step of water process amount prediction technique of desalted water station.
The computer program of the water process amount prediction technique of fired power generating unit desalted water station provided by the embodiment of the present application produces
Product, the computer readable storage medium including storing program code, the instruction that said program code includes can be used in execution
The step of stating the water process amount prediction technique of fired power generating unit desalted water station described in embodiment of the method, for details, reference can be made to above-mentioned sides
Method embodiment, details are not described herein.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description
It with the specific work process of device, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.In the application
In provided several embodiments, it should be understood that disclosed systems, devices and methods, it can be real by another way
It is existing.The apparatus embodiments described above are merely exemplary, for example, the division of the unit, only a kind of logic function
It can divide, there may be another division manner in actual implementation, in another example, multiple units or components can combine or can collect
At another system is arrived, or some features can be ignored or not executed.Another point, shown or discussed mutual coupling
Conjunction or direct-coupling or communication connection can be the indirect coupling or communication connection by some communication interfaces, device or unit,
It can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in the executable non-volatile computer-readable storage medium of a processor.Based on this understanding, the application
Technical solution substantially the part of the part that contributes to existing technology or the technical solution can be with software in other words
The form of product embodies, which is stored in a storage medium, including some instructions use so that
One computer equipment (can be personal computer, server or the network equipment etc.) executes each embodiment institute of the application
State all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-Only
Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. is various to deposit
Store up the medium of program code.
Finally, it should be noted that embodiment described above, the only specific embodiment of the application, to illustrate the application
Technical solution, rather than its limitations, the protection scope of the application is not limited thereto, although with reference to the foregoing embodiments to this Shen
It please be described in detail, those skilled in the art should understand that: anyone skilled in the art
Within the technical scope of the present application, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of the embodiment of the present application technical solution, should all cover the protection in the application
Within the scope of.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.
Claims (10)
1. a kind of water process amount prediction technique of fired power generating unit desalted water station characterized by comprising
Obtain desalted water station type, boiler type, the hydrogen generator station type of target fired power generating unit desalted water station, desalted water station investment fortune
Capable duration, fired power generating unit the power generation durations of multiple historical time sections, fired power generating unit each historical time section hair
Electricity, fired power generating unit the estimated power generation duration of at least one future time section, fired power generating unit it is described at least one it is following when
Between section estimated generated energy；
According to the desalted water station type, boiler type, hydrogen generator station type, the duration that desalted water station puts into operation, fired power generating unit
In the power generation durations of multiple historical time sections, fired power generating unit in the generated energy of each historical time section, fired power generating unit extremely
The estimated power generation duration of a few future time section, fired power generating unit at least one future time section estimated generated energy,
And the water process amount prediction model of fired power generating unit desalted water station trained in advance, obtain the target fired power generating unit desalted water station
In the water process amount of each future time section.
2. the method according to claim 1, wherein the water process amount of the fired power generating unit desalted water station predicts mould
Type includes deep learning model；
The deep learning model includes: Recognition with Recurrent Neural Network and Fusion Features network；
Using the following manner training deep learning model:
Sample desalted water station type, boiler type, the hydrogen generator station type of multiple sample fired power generating unit desalted water stations are obtained, sample removes
The duration that salt water station puts into operation, power generation duration, sample fired power generating unit of the sample fired power generating unit in multiple sample historical time sections
The generated energy of each sample historical time section, sample fired power generating unit desalted water station each sample historical time section practical water
Treating capacity；
According to sample fired power generating unit in the power generation durations of multiple sample historical time sections, sample fired power generating unit in each sample history
The generated energy of period generates characteristic vector sequence according to the sequencing of sample historical time section；Sampling feature vectors sequence
In, including multiple first sample feature vectors；
According to sample desalted water station type, boiler type, the hydrogen generator station type of sample fired power generating unit desalted water station, sample demineralized water
The duration that station is put into operation constitutes the second sampling feature vectors of each sample fired power generating unit desalted water station；
By sampling feature vectors sequence inputting into Recognition with Recurrent Neural Network, acquisition is respectively corresponded with each first sample feature vector
Median feature vector；
For each first sample feature vector, which is spliced with the second sampling feature vectors,
It forms sample corresponding with the first sample feature vector and splices vector；
The corresponding sample splicing vector of each first sample feature vector is input in Fusion Features network respectively, obtains and is somebody's turn to do
The corresponding water process amount prediction result of first sample feature vector；
According to the corresponding water process amount prediction result of each first sample feature vector and each first sample feature to
Measure the practical water process amount of corresponding sample historical time section, training Recognition with Recurrent Neural Network and Fusion Features network.
3. according to the method described in claim 2, it is characterized in that, described obtain the target fired power generating unit desalted water station not
Carry out the water process amount of period, comprising:
According to fired power generating unit the power generation durations of multiple historical time sections, fired power generating unit each historical time section power generation
Amount, fired power generating unit are in the estimated power generation duration of at least one future time section, fired power generating unit at least one described future time
The estimated generated energy of section generates characteristic vector sequence according to the sequencing of each the historical time section and future time section；
Described eigenvector sequence includes multiple first eigenvectors；
According to the desalted water station type, boiler type, hydrogen generator station type of target fired power generating unit desalted water station, desalted water station investment fortune
Capable duration generates second feature vector；
By described eigenvector sequence inputting to Recognition with Recurrent Neural Network, median feature vector is obtained；
Each median feature vector is spliced with the second feature vector respectively, generate with each intermediate features to
Corresponding splicing vector is measured, and each splicing vector is input in the Fusion Features network, obtains the mesh
Fired power generating unit desalted water station is marked in the water process amount of each future time section.
4. the method according to claim 1, wherein this method further include:
According to the target fired power generating unit desalted water station in the water process amount of future time section, determine that the target fired power generating unit is removed
Ultrafiltration apparatus, active carbon filtration system in salt water station, reverse osmosis treatment system and ion-exchange treatment system will be in the future
The runing time and operation power of period.
5. the method according to claim 1, wherein this method further include:
According to the target fired power generating unit desalted water station in the water process amount of future time section, discharge wastewater flow rate is determined.
6. a kind of water process amount prediction meanss of fired power generating unit desalted water station characterized by comprising
Module is obtained, for obtaining the desalted water station type, boiler type, hydrogen generator station type of target fired power generating unit desalted water station,
The duration that desalted water station puts into operation, fired power generating unit is in the power generation durations of multiple historical time sections, fired power generating unit each described
The generated energy of historical time section, fired power generating unit are in the estimated power generation duration of at least one future time section, fired power generating unit described
The estimated generated energy of at least one future time section；
Prediction module is used for according to the desalted water station type, boiler type, hydrogen generator station type, what desalted water station put into operation
Duration, fired power generating unit the power generation durations of multiple historical time sections, fired power generating unit each historical time section generated energy,
Fired power generating unit is in the estimated power generation duration of at least one future time section, fired power generating unit at least one future time section
It is expected that generated energy, and the water process amount prediction model of fired power generating unit desalted water station trained in advance, obtain the target thermoelectricity
Water process amount of the unit desalted water station in each future time section.
7. device according to claim 6, which is characterized in that the water process amount of the fired power generating unit desalted water station predicts mould
Type includes deep learning model；
The deep learning model includes: Recognition with Recurrent Neural Network and Fusion Features network；
Further include: model training module, for using the following manner training deep learning model:
Sample desalted water station type, boiler type, the hydrogen generator station type of multiple sample fired power generating unit desalted water stations are obtained, sample removes
The duration that salt water station puts into operation, power generation duration, sample fired power generating unit of the sample fired power generating unit in multiple sample historical time sections
The generated energy of each sample historical time section, sample fired power generating unit desalted water station each sample historical time section practical water
Treating capacity；
According to sample fired power generating unit in the power generation durations of multiple sample historical time sections, sample fired power generating unit in each sample history
The generated energy of period generates characteristic vector sequence according to the sequencing of sample historical time section；Sampling feature vectors sequence
In, including multiple first sample feature vectors；
According to sample desalted water station type, boiler type, the hydrogen generator station type of sample fired power generating unit desalted water station, sample demineralized water
The duration that station is put into operation constitutes the second sampling feature vectors of each sample fired power generating unit desalted water station；
By sampling feature vectors sequence inputting into Recognition with Recurrent Neural Network, acquisition is respectively corresponded with each first sample feature vector
Median feature vector；
For each first sample feature vector, which is spliced with the second sampling feature vectors,
It forms sample corresponding with the first sample feature vector and splices vector；
The corresponding sample splicing vector of each first sample feature vector is input in Fusion Features network respectively, obtains and is somebody's turn to do
The corresponding water process amount prediction result of first sample feature vector；
According to the corresponding water process amount prediction result of each first sample feature vector and each first sample feature to
Measure the practical water process amount of corresponding sample historical time section, training Recognition with Recurrent Neural Network and Fusion Features network.
8. device according to claim 7, which is characterized in that the prediction module, for obtaining institute using following manner
Target fired power generating unit desalted water station is stated in the water process amount of future time section:
According to fired power generating unit the power generation durations of multiple historical time sections, fired power generating unit each historical time section power generation
Amount, fired power generating unit are in the estimated power generation duration of at least one future time section, fired power generating unit at least one described future time
The estimated generated energy of section generates characteristic vector sequence according to the sequencing of each the historical time section and future time section；
Described eigenvector sequence includes multiple first eigenvectors；
According to the desalted water station type, boiler type, hydrogen generator station type of target fired power generating unit desalted water station, desalted water station investment fortune
Capable duration generates second feature vector；
By described eigenvector sequence inputting to Recognition with Recurrent Neural Network, median feature vector is obtained；
Each median feature vector is spliced with the second feature vector respectively, generate with each intermediate features to
Corresponding splicing vector is measured, and each splicing vector is input in the Fusion Features network, obtains the mesh
Fired power generating unit desalted water station is marked in the water process amount of each future time section.
9. device according to claim 6, which is characterized in that the device further include:
First determining module, for, in the water process amount of future time section, being determined according to the target fired power generating unit desalted water station
Ultrafiltration apparatus, active carbon filtration system, reverse osmosis treatment system and ion exchange in the target fired power generating unit desalted water station
Runing time and operation power of the processing system in the future time section.
10. device according to claim 6, which is characterized in that the device further include:
Second determining module, for, in the water process amount of future time section, being determined according to the target fired power generating unit desalted water station
Wastewater flow rate is discharged.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910462217.7A CN110135661B (en) | 2019-05-30 | 2019-05-30 | Water treatment capacity prediction method and device for desalting water station of thermal power generating unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910462217.7A CN110135661B (en) | 2019-05-30 | 2019-05-30 | Water treatment capacity prediction method and device for desalting water station of thermal power generating unit |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110135661A true CN110135661A (en) | 2019-08-16 |
| CN110135661B CN110135661B (en) | 2021-06-25 |
Family
ID=67582840
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910462217.7A Active CN110135661B (en) | 2019-05-30 | 2019-05-30 | Water treatment capacity prediction method and device for desalting water station of thermal power generating unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110135661B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004267865A (en) * | 2003-03-06 | 2004-09-30 | Hitachi Ltd | Support system of water treatment process |
| CN109242196A (en) * | 2018-09-25 | 2019-01-18 | 中国水利水电科学研究院 | Water consumption amount prediction technique and device |
| CN109299834A (en) * | 2018-12-03 | 2019-02-01 | 中国水利水电科学研究院 | A kind of the water process amount prediction technique and device of water treatment plant |
-
2019
- 2019-05-30 CN CN201910462217.7A patent/CN110135661B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004267865A (en) * | 2003-03-06 | 2004-09-30 | Hitachi Ltd | Support system of water treatment process |
| CN109242196A (en) * | 2018-09-25 | 2019-01-18 | 中国水利水电科学研究院 | Water consumption amount prediction technique and device |
| CN109299834A (en) * | 2018-12-03 | 2019-02-01 | 中国水利水电科学研究院 | A kind of the water process amount prediction technique and device of water treatment plant |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110135661B (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Perera et al. | Machine learning techniques for supporting renewable energy generation and integration: a survey | |
| Soares et al. | Distributed energy resource short-term scheduling using Signaled Particle Swarm Optimization | |
| CN107317334B (en) | A kind of electric system rack reconstructing method and device | |
| US9887544B2 (en) | System and method for mathematical predictive analytics and computational energy modeling | |
| Bremer et al. | Sampling the Search Space of Energy Resources for Self-organized, Agent-based Planning of Active Power Provision. | |
| KR102105192B1 (en) | Operation system and method for virtual power plant using modeling | |
| CN109977552A (en) | A kind of equipment method for predicting residual useful life and system considering that state-detection influences | |
| Beldiceanu et al. | Describing and generating solutions for the EDF unit commitment problem with the ModelSeeker | |
| CN114581781B (en) | Target detection method and device for high-resolution remote sensing image | |
| Riley | Discrete-event simulation optimization: a review of past approaches and propositions for future direction. | |
| Jain | Interaction between software engineering and artificial intelligence-a review | |
| Leithon et al. | Task scheduling strategies for utility maximization in a renewable-powered IoT node | |
| EP3961507A1 (en) | Optimal policy learning and recommendation for distribution task using deep reinforcement learning model | |
| CN114567560A (en) | Edge node dynamic resource allocation method based on generation confrontation simulation learning | |
| CN110135661A (en) | A kind of the water process amount prediction technique and device of fired power generating unit desalted water station | |
| Jung et al. | Performance models for large scale multiagent systems: using distributed POMDP building blocks | |
| CN112417748A (en) | Method, system, equipment and medium for scheduling automatic driving simulation task | |
| Ender et al. | A framework for portfolio management of renewable hybrid energy sources | |
| CN110092507A (en) | A kind of method and device of Industrial Wastewater Treatment | |
| KR102069664B1 (en) | Publication system and method of electronic cash for electric power transaction | |
| CN106228029A (en) | Quantification problem method for solving based on mass-rent and device | |
| CN115864364A (en) | Operation strategy planning method and device for user to participate in demand response | |
| Papadaskalopoulos et al. | Participation of electric vehicles in electricity markets through a decentralized mechanism | |
| CN117371681A (en) | Power resource scheduling method, device, equipment and storage medium | |
| Švogor et al. | Multi-criteria software component allocation on a heterogeneous platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |