CN105590144A - Wind speed prediction method and apparatus based on NARX neural network - Google Patents
Wind speed prediction method and apparatus based on NARX neural network Download PDFInfo
- Publication number
- CN105590144A CN105590144A CN201511019002.6A CN201511019002A CN105590144A CN 105590144 A CN105590144 A CN 105590144A CN 201511019002 A CN201511019002 A CN 201511019002A CN 105590144 A CN105590144 A CN 105590144A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- data
- neutral net
- narx
- ymin
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title abstract description 13
- 238000013528 artificial neural network Methods 0.000 title abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000010606 normalization Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000012360 testing method Methods 0.000 claims abstract description 6
- 230000007935 neutral effect Effects 0.000 claims description 37
- 238000013277 forecasting method Methods 0.000 claims description 15
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 claims description 6
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 4
- 230000000694 effects Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 230000005611 electricity Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000013256 coordination polymer Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005183 dynamical system Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a wind speed prediction method and an apparatus based on an NARX neural network. The method includes: acquiring historical data of related parameters required by wind speed prediction, wherein the related parameters including wind speed, pitch angle, rotating speed, and power; performing normalization processing of the acquired data; inputting the processed data to the NARX neural network as a training sample for training; and inputting a test sample to the trained NARX neural network, performing reverse normalization of an output value, and obtaining a practical prediction value. According to the method and the apparatus, the model is built for the prediction of the wind speed by employing the NARX neural network, input parameters of the network are selected by employing formulas and principles of fan aerodynamics, the prediction is convenient, the accuracy is high, the wind energy capturing capability and the generating capacity are increased, and the method and the apparatus are applicable to be promoted and applied.
Description
Technical field
The present invention relates to wind-powered electricity generation control technology field, particularly relate to a kind of (non-based on NARX neutral netLinear Recurrent neural network) wind speed forecasting method and device.
Background technology
Under the support of national industrial policies, nearly ten years, Wind Power In China industry has experienced advances by leaps and boundsThe growth of formula, China has become genuine wind-powered electricity generation big country, and the large of wind-powered electricity generation and regenerative resource sent outExhibition is following irreversible trend. In the past few years, the emphasis of Wind Power Generation is from high wind speed to low wind speedZone-transfer, Wind Power In China complete machine enterprise is by autonomous innovation, the larger single-machine capacity of active development, moreLarge impeller, adapt to lower wind speed, more intelligent new architecture, constantly promote wind-resources potentiality to be exploited andWind Power Utilization level. The ultralow wind speed blower fan that wind energy utilization efficiency is higher continues to bring out.
It is most important that the Measurement accuracy of wind speed absorbs wind energy to greatest extent for speed-changing draught fan, particularlyBelow rated wind speed time, wind speed is the important parameter that becomes oar control and torque control. And wind speed is bulliedThe impact of the many factors such as pressure and temperature, randomness is very large, and the difficulty of Accurate Prediction is very large. At presentCommon Forecasting Methodology has neural network, Kalman filtering method, time series method etc. The wherein timeSerial method in the difficult parameters of high-order model to determine that to cause precision of prediction not high; Kalman filtering method forThe difficulty of Prediction of Nonlinear Dynamical Systems is larger; Neural network is because it is for the distinctive advantage of nonlinear systemFurtherd investigate in recent years. But model structure has substantially all adopted traditional backpropagation neural network (BPNetwork), precision of prediction is not very high; As patent CN104112166A, a kind of short-term wind of wind energy turbine setSpeed Forecasting Methodology and system have adopted BP network exactly, training data are processed simultaneously. PatentCN103927460A, a kind of short-term wind speed forecasting method of wind farm based on RBF, has adopted RBFNeutral net, carries out normalizing and renormalization to inputoutput data, with temperature, humidity, air pressure andWind direction is as input, but fails to make full use of the impact of historical data for prediction of wind speed.
As can be seen here, above-mentioned existing wind speed forecasting method obviously still has inconvenience and defect, and urgentlyWait to be further improved. How to found one and can make full use of existing blower fan hardware and monitoringData, accurately, wind speed forecasting method and device easily, becoming the current industry utmost point needs improved orderMark.
Summary of the invention
The technical problem to be solved in the present invention be to provide one can make full use of existing blower fan hardware andMonitor data, accurately, wind speed forecasting method and device easily.
For achieving the above object, the present invention adopts following technical scheme:
Based on a wind speed forecasting method for NARX neutral net, comprise the steps: steps A, adoptThe historical data of collection forecasting wind speed required relevant parameter, described relevant parameter comprise wind speed, propeller pitch angle,Rotating speed and power; Step B, is normalized the data that collect; Step C, after processingData be input in NARX neutral net and train as training sample; Step D, by test specimensOriginally be input in the NARX neutral net training, and output valve is carried out to renormalization, obtain realityPredicted value.
Further, in described step B, the data after normalized also need to arrange at random by groupOrder processing.
Further, described NARX neutral net haves three layers altogether, is respectively input layer, hidden layer and outputLayer; Input layer number is 4, is respectively power, propeller pitch angle, rotating speed and wind speed; Hidden layer godIt is 8 through first number; Output layer nodes is 1, the predicted value of representative to following moment wind speed;The time delay exponent number of output is 2.
Further, in described step B normalized according to following formula:
y＝(ymax-ymin)*(x-xmin)/(xmax-xmin)+ymin
Wherein, ymax and ymin are respectively maximum and the minimum of a value of data area after normalization; XmaxBe respectively maximum and the minimum of a value of data before normalization with xmin; Y is the data after normalization, xFor the data before normalization, described ymax and ymin get respectively 1 and-1.
A forecasting wind speed device based on NARX neutral net, comprising: acquisition module, gathers wind speedPredict the historical data of required relevant parameter, described relevant parameter comprise wind speed, propeller pitch angle, rotating speed andPower; Processing module, is normalized the data that collect; Training module, after processingData be input in NARX neutral net and train as training sample; Calculate output module, willTest sample book is input in the NARX neutral net training, and output valve is carried out to renormalization,To actual prediction value.
Further, described processing module, also needs to be undertaken at random by group to the data after normalizedSequence is processed.
Further, described NARX neutral net haves three layers altogether, is respectively input layer, hidden layer and outputLayer; Input layer number is 4, is respectively power, propeller pitch angle, rotating speed and wind speed; Hidden layer godIt is 8 through first number; Output layer nodes is 1, the predicted value of representative to following moment wind speed;The time delay exponent number of output is 2.
Further, described processing module, normalized is according to following formula:
y＝(ymax-ymin)*(x-xmin)/(xmax-xmin)+ymin
Wherein, ymax and ymin are respectively maximum and the minimum of a value of data area after normalization; XmaxBe respectively maximum and the minimum of a value of data before normalization with xmin; Y is the data after normalization, xFor the data before normalization, described ymax and ymin get respectively 1 and-1.
By adopting technique scheme, the present invention at least has the following advantages:
1, the present invention has adopted NARX neural network model to predict wind speed, has adoptedNew model improves the forecasting wind speed with convenient wind power generating set, catches thereby improve wind energyAbility, and then improve generated energy. The present invention utilizes the dynamic (dynamical) formula of blower air and principle to selectThe input parameter of network, the i.e. relevant parameter of forecasting wind speed. Be different from traditional wind speed forecasting method normalThe normal information such as humidity, temperature and air pressure of selecting are as nerve network input parameter, and parameter of the present invention is selectedMore be conducive to real-time measurement, thereby improve the accuracy of prediction.
2, the data pretreatment before training, except normalization, has also carried out random row to each group of sampleOrder, can increase like this knowledge quantity of NARX neural network learning and improve the knowledge to following new dataOther ability. Because training sample has been carried out to pretreatment, there is higher learning efficiency and training effect.
3, NARX neutral net of the present invention has effectively been utilized wind speed correlation factor data, has brought into playSeasonal effect in time series effect, has further improved prediction effect.
4, the present invention makes full use of existing blower fan hardware and monitor data, does not need additionally to increase hardware,Only this algorithm need be joined in the primary control program of blower fan, then be uploaded to the existing master controller of blower fanCan realize.
Brief description of the drawings
Above-mentioned is only the general introduction of technical solution of the present invention, in order to better understand technology of the present inventionMeans, below in conjunction with accompanying drawing and detailed description of the invention, the present invention is described in further detail.
Fig. 1 is a kind of stream of the wind speed forecasting method based on NARX neutral net that the embodiment of the present application providesCheng Tu;
Fig. 2 is a kind of forecasting wind speed device knot based on NARX neutral net that the embodiment of the present application providesStructure block diagram;
Fig. 3 is traditional BP neutral net forecasting wind speed result curve figure;
Fig. 4 is the forecasting wind speed knot that adopts the wind speed forecasting method based on NARX neutral net of the present inventionFruit curve map;
Fig. 5 is forecasting wind speed comparison diagram (method of the present invention and traditional BP neutral net forecasting wind speed pairThan).
Detailed description of the invention
Embodiment 1
As shown in Figure 1, a kind of wind speed forecasting method based on NARX neutral net of the present embodiment, bagDraw together following steps:
Steps A, gathers the historical data of forecasting wind speed required relevant parameter, relevant parameter comprise wind speed,Propeller pitch angle, rotating speed and power, according to the Aerodynamics Model of blower fan, known power is wind speed, oarThe function of elongation and rotating speed, therefore gathering above-mentioned data, to carry out network training as follows:
Pm＝1/2×CP(λ,β)ρπR2v3＝f(v,ω,β)
Step B, is normalized the data that collect, for neural metwork training ready,According to following formula:
y＝(ymax-ymin)*(x-xmin)/(xmax-xmin)+ymin
Wherein, ymax and ymin are respectively maximum and the minimum of a value of data area after normalization; XmaxBe respectively maximum and the minimum of a value of data before normalization with xmin; Y is the data after normalization, xFor the data before normalization, described ymax and ymin get respectively 1 and-1 conventionally.
Step C, is input to data after treatment as training sample in NARX neutral net and instructsPractice.
Wherein, in order further to improve learning efficiency and training effect, preferably, by normalizedAfter data first carry out randomly ordered processing by group, and then input as training sample. Wherein group isRefer to one group of corresponding historical wind speed, propeller pitch angle, rotating speed, power (these 4 is network input) and prediction windSpeed (network output).
The relevant training data of wind speed that NARX neutral net generates before can utilizing builds. NARXNeutral net, network haves three layers altogether, is respectively input layer, hidden layer and output layer. Input layerNumber, for the quantity of forecasting wind speed correlative factor, 4, is respectively power, propeller pitch angle, rotating speed and mistakeRemove wind speed. It is 8 that hidden neuron number obtains by experience and experiment. Output layer nodes is 1Individual, the predicted value of representative to following moment wind speed. The time delay exponent number of output is 2.
Step D, is input to test sample book in the NARX neutral net training, and output valve is enteredRow renormalization, obtains actual prediction value. Wherein test sample book is the new data outside training sample.
Through the training and testing of actual wind field 2MW blower fan data, method of the present invention is compared traditionalBP neutral net, forecasting wind speed error can be decreased to-0.25 by approximately-4 to 4m/s and (join to 0.25m/sClose shown in Fig. 3,4), and adopt prediction of wind speed and the actual wind speed of inventive method comparatively approaching, errorLess (as shown in Figure 5).
Embodiment 2
As shown in Figure 2, a kind of forecasting wind speed device based on NARX neutral net of the present embodiment, bagDraw together acquisition module, processing module, training module and calculating output module, specific as follows:
Acquisition module, the historical data of the required relevant parameter of collection forecasting wind speed, relevant parameter comprises windSpeed, propeller pitch angle, rotating speed and power. According to the Aerodynamics Model of blower fan, known power be wind speed,The function of propeller pitch angle and rotating speed, therefore gathering above-mentioned data, to carry out network training as follows:
Pm＝1/2×CP(λ,β)ρπR2v3＝f(v,ω,β)
Processing module, is normalized the data that collect, for neural metwork training is carried out standardStandby, according to following formula:
y＝(ymax-ymin)*(x-xmin)/(xmax-xmin)+ymin
Wherein, ymax and ymin are respectively maximum and the minimum of a value of data area after normalization; XmaxBe respectively maximum and the minimum of a value of data before normalization with xmin; Y is the data after normalization, xFor the data before normalization, described ymax and ymin get respectively 1 and-1 conventionally.
Training module, is input to data after treatment as training sample in NARX neutral net and carries outTraining.
Wherein, in order further to improve learning efficiency and training effect, preferably, by normalizedAfter data first carry out randomly ordered processing by group, and then input as training sample. Wherein group isRefer to corresponding one group of historical wind speed, propeller pitch angle, rotating speed, power and institute's prediction of wind speed.
The relevant training data of wind speed that NARX neutral net generates before can utilizing builds. NARXNeutral net, network haves three layers altogether, is respectively input layer, hidden layer and output layer. Input layerNumber, for the quantity of forecasting wind speed correlative factor, 4, is respectively power, propeller pitch angle, rotating speed and mistakeRemove wind speed. It is 8 that hidden neuron number obtains by experience and experiment. Output layer nodes is 1Individual, the predicted value of representative to following moment wind speed. The time delay exponent number of output is 2.
Calculate output module, test sample book is input in the NARX neutral net training, and by defeatedGo out value and carry out renormalization, obtain actual prediction value. Wherein test sample book is new outside training sampleData.
The above, be only preferred embodiment of the present invention, not the present invention made to any formOn restriction, those skilled in the art utilize the technology contents of above-mentioned announcement make a little simple modification,Equivalent variations or modification, all drop in protection scope of the present invention.
Claims (8)
1. the wind speed forecasting method based on NARX neutral net, is characterized in that, comprises as followsStep:
Steps A, the historical data of the required relevant parameter of collection forecasting wind speed, required relevant parameter comprises windSpeed, propeller pitch angle, rotating speed and power;
Step B, is normalized the data that collect;
Step C, is input to data after treatment as training sample in NARX neutral net and instructsPractice;
Step D, is input to test sample book in the NARX neutral net training, and output valve is enteredRow renormalization, obtains actual prediction value.
2. the wind speed forecasting method based on NARX neutral net according to claim 1, its spyLevy and be, in described step B, the data after normalized also need to carry out randomly ordered processing by group.
3. the wind speed forecasting method based on NARX neutral net according to claim 1, its spyLevy and be, described NARX neutral net haves three layers altogether, is respectively input layer, hidden layer and output layer; DefeatedEntering layer neuron number is 4, is respectively power, propeller pitch angle, rotating speed and wind speed; Hidden neuronNumber is 8; Output layer nodes is 1, the predicted value of representative to following moment wind speed; OutputTime delay exponent number is 2.
4. the wind speed forecasting method based on NARX neutral net according to claim 1, its spyLevy and be, in described step B, normalized is according to following formula:
y＝(ymax-ymin)*(x-xmin)/(xmax-xmin)+ymin
Wherein, ymax and ymin are respectively maximum and the minimum of a value of data area after normalization; XmaxBe respectively maximum and the minimum of a value of data before normalization with xmin; Y is the data after normalization, xFor the data before normalization, described ymax and ymin get respectively 1 and-1.
5. the forecasting wind speed device based on NARX neutral net, is characterized in that, comprising:
Acquisition module, the historical data of the required relevant parameter of collection forecasting wind speed, described relevant parameter bagDraw together wind speed, propeller pitch angle, rotating speed and power;
Processing module, is normalized the data that collect;
Training module, is input to data after treatment as training sample in NARX neutral net and carries outTraining;
Calculate output module, test sample book is input in the NARX neutral net training, and by defeatedGo out value and carry out renormalization, obtain actual prediction value.
6. the forecasting wind speed device based on NARX neutral net according to claim 5, its spyLevy and be, described processing module, the data after normalized also need to carry out randomly ordered processing by group.
7. the forecasting wind speed device based on NARX neutral net according to claim 5, its spyLevy and be, described NARX neutral net haves three layers altogether, is respectively input layer, hidden layer and output layer; DefeatedEntering layer neuron number is 4, is respectively power, propeller pitch angle, rotating speed and wind speed; Hidden neuronNumber is 8; Output layer nodes is 1, the predicted value of representative to following moment wind speed; OutputTime delay exponent number is 2.
8. the forecasting wind speed device based on NARX neutral net according to claim 5, its spyLevy and be, described processing module, normalized is according to following formula:
y＝(ymax-ymin)*(x-xmin)/(xmax-xmin)+ymin
Wherein, ymax and ymin are respectively maximum and the minimum of a value of data area after normalization; XmaxBe respectively maximum and the minimum of a value of data before normalization with xmin; Y is the data after normalization, xFor the data before normalization, described ymax and ymin get respectively 1 and-1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511019002.6A CN105590144A (en) | 2015-12-30 | 2015-12-30 | Wind speed prediction method and apparatus based on NARX neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511019002.6A CN105590144A (en) | 2015-12-30 | 2015-12-30 | Wind speed prediction method and apparatus based on NARX neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105590144A true CN105590144A (en) | 2016-05-18 |
Family
ID=55929710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511019002.6A Pending CN105590144A (en) | 2015-12-30 | 2015-12-30 | Wind speed prediction method and apparatus based on NARX neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105590144A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446419A (en) * | 2016-09-27 | 2017-02-22 | 广东电网有限责任公司电力科学研究院 | Modeling method and system of coal-fired boiler in thermal power plant |
| CN107045574A (en) * | 2017-04-12 | 2017-08-15 | 浙江大学 | The low wind speed section effective wind speed method of estimation of wind power generating set based on SVR |
| CN107067076A (en) * | 2017-05-27 | 2017-08-18 | 重庆大学 | A kind of passenger flow forecasting based on time lag NARX neutral nets |
| CN107451701A (en) * | 2017-08-15 | 2017-12-08 | 广东工业大学 | A kind of method and system of the forecasting wind speed based on dynamic neural network |
| CN108596380A (en) * | 2018-04-18 | 2018-09-28 | 中国科学院国家空间科学中心 | A kind of quantitative detection method of sea Typhoon Wind Field |
| CN108647778A (en) * | 2018-05-09 | 2018-10-12 | 天津大学 | Dynamic prediction method for drainage flow of drainage port of urban rainwater system |
| CN110083854A (en) * | 2018-12-18 | 2019-08-02 | 太原理工大学 | A kind of Separators in High-Speed Ball Bearings stability prediction method |
| CN110458342A (en) * | 2019-07-26 | 2019-11-15 | 国网江苏省电力有限公司金湖县供电分公司 | One kind monitoring system and method based on improved NARX neural network microclimate |
| CN111754045A (en) * | 2020-06-30 | 2020-10-09 | 四川生态诚品农业开发有限公司 | Prediction system based on fruit tree growth |
| CN112742187A (en) * | 2020-12-10 | 2021-05-04 | 山西漳山发电有限责任公司 | Method and device for controlling pH value in desulfurization system |
| CN113450564A (en) * | 2021-05-21 | 2021-09-28 | 江苏大学 | Intersection passing method based on NARX neural network and C-V2X technology |
-
2015
- 2015-12-30 CN CN201511019002.6A patent/CN105590144A/en active Pending
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446419A (en) * | 2016-09-27 | 2017-02-22 | 广东电网有限责任公司电力科学研究院 | Modeling method and system of coal-fired boiler in thermal power plant |
| CN107045574B (en) * | 2017-04-12 | 2020-02-28 | 浙江大学 | SVR-based effective wind speed estimation method for low wind speed section of wind generating set |
| CN107045574A (en) * | 2017-04-12 | 2017-08-15 | 浙江大学 | The low wind speed section effective wind speed method of estimation of wind power generating set based on SVR |
| CN107067076A (en) * | 2017-05-27 | 2017-08-18 | 重庆大学 | A kind of passenger flow forecasting based on time lag NARX neutral nets |
| CN107451701A (en) * | 2017-08-15 | 2017-12-08 | 广东工业大学 | A kind of method and system of the forecasting wind speed based on dynamic neural network |
| CN108596380A (en) * | 2018-04-18 | 2018-09-28 | 中国科学院国家空间科学中心 | A kind of quantitative detection method of sea Typhoon Wind Field |
| CN108596380B (en) * | 2018-04-18 | 2022-11-08 | 中国科学院国家空间科学中心 | Quantitative detection method for sea surface typhoon wind field |
| CN108647778A (en) * | 2018-05-09 | 2018-10-12 | 天津大学 | Dynamic prediction method for drainage flow of drainage port of urban rainwater system |
| CN108647778B (en) * | 2018-05-09 | 2022-02-25 | 天津大学 | Dynamic prediction method for drainage flow of drainage port of urban rainwater system |
| CN110083854A (en) * | 2018-12-18 | 2019-08-02 | 太原理工大学 | A kind of Separators in High-Speed Ball Bearings stability prediction method |
| CN110083854B (en) * | 2018-12-18 | 2022-04-22 | 太原理工大学 | High-speed ball bearing retainer stability prediction method |
| CN110458342A (en) * | 2019-07-26 | 2019-11-15 | 国网江苏省电力有限公司金湖县供电分公司 | One kind monitoring system and method based on improved NARX neural network microclimate |
| CN111754045A (en) * | 2020-06-30 | 2020-10-09 | 四川生态诚品农业开发有限公司 | Prediction system based on fruit tree growth |
| CN112742187A (en) * | 2020-12-10 | 2021-05-04 | 山西漳山发电有限责任公司 | Method and device for controlling pH value in desulfurization system |
| CN113450564A (en) * | 2021-05-21 | 2021-09-28 | 江苏大学 | Intersection passing method based on NARX neural network and C-V2X technology |
| CN113450564B (en) * | 2021-05-21 | 2022-08-23 | 江苏大学 | Intersection passing method based on NARX neural network and C-V2X technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105590144A (en) | Wind speed prediction method and apparatus based on NARX neural network | |
| Li et al. | Self-attention ConvLSTM and its application in RUL prediction of rolling bearings | |
| CN104632521B (en) | A kind of wind power optimization system and method based on drift correction | |
| CN103065202B (en) | Wind power plant ultrashort term wind speed prediction method based on combination kernel function | |
| Asghar et al. | Estimation of wind turbine power coefficient by adaptive neuro-fuzzy methodology | |
| CN104915747A (en) | Electricity generation performance evaluation method of generator set and equipment thereof | |
| CN103808509A (en) | Fan gear box fault diagnosis method based on artificial intelligence algorithm | |
| CN107392304A (en) | A kind of Wind turbines disorder data recognition method and device | |
| CN104036073B (en) | Double-fed wind power plant dynamic equivalence modeling method suitable for active power characteristic analysis | |
| CN109029974A (en) | A kind of epicyclic gearbox fault detection method based on one-dimensional convolutional neural networks | |
| CN110994604A (en) | Electric power system transient stability evaluation method based on LSTM-DNN model | |
| CN110363334B (en) | Grid line loss prediction method of photovoltaic grid connection based on gray neural network model | |
| CN107045574B (en) | SVR-based effective wind speed estimation method for low wind speed section of wind generating set | |
| CN113935534A (en) | Photovoltaic day-ahead prediction method, system and equipment based on convolution transform architecture | |
| CN104763585A (en) | Distributed data collection based wind turbine generator unit dynamic reconfiguring method | |
| Dimitrov et al. | From SCADA to lifetime assessment and performance optimization: how to use models and machine learning to extract useful insights from limited data | |
| CN107527093B (en) | Wind turbine generator running state diagnosis method and device | |
| CN115469184A (en) | New energy transmission line fault identification method based on convolutional network | |
| CN113240217A (en) | Photovoltaic power generation prediction method and device based on integrated prediction model | |
| Asghar et al. | Online estimation of wind turbine tip speed ratio by adaptive neuro-fuzzy algorithm | |
| CN104376386A (en) | Method for predicating power of wind turbine in wind farm | |
| CN104991447A (en) | Thermal power generating unit variable-load speed predicting method based on wavelet neural network | |
| CN114320773A (en) | Wind turbine generator fault early warning method based on power curve analysis and neural network | |
| Fadzail et al. | Application of Automated Machine Learning (AutoML) method in wind turbine fault detection | |
| Bai et al. | Short-term prediction models for wind speed and wind power |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Chu Jingchun Inventor after: Huo Feng Inventor after: Zhang Xuesong Inventor after: Liu Zhongpeng Inventor after: Ji Guorui Inventor after: Dai Haitao Inventor after: Feng Jian Inventor before: Huo Feng Inventor before: Zhang Xuesong Inventor before: Liu Zhongpeng Inventor before: Ji Guorui Inventor before: Dai Haitao Inventor before: Feng Jian |
|
| CB03 | Change of inventor or designer information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160518 |
|
| RJ01 | Rejection of invention patent application after publication |