CN109737008A - Wind turbines intelligence variable blade control system and method, Wind turbines - Google Patents
Wind turbines intelligence variable blade control system and method, Wind turbines Download PDFInfo
- Publication number
- CN109737008A CN109737008A CN201910115874.4A CN201910115874A CN109737008A CN 109737008 A CN109737008 A CN 109737008A CN 201910115874 A CN201910115874 A CN 201910115874A CN 109737008 A CN109737008 A CN 109737008A
- Authority
- CN
- China
- Prior art keywords
- wind turbines
- speed
- rated
- wind
- controller
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Abstract
The invention discloses a kind of Wind turbines intelligence variable blade control system and methods, Wind turbines.The system includes: pitch control device, for obtaining the deviation between the real-time revolving speed of Wind turbines and rated speed, and according to the deviation, the variable pitch angle reference value that Wind turbines are carried out with pitch control is calculated using PI controller.Wind turbines intelligence variable blade control system provided by the invention and method, Wind turbines, using prediction of wind speed as the important input of fan master control system, optimal PI controller is designed, allows to reduce the gap of generator speed measured value and rated value to greatest extent.
Description
Technical field
The present invention relates to technical field of wind power generation, more particularly to a kind of Wind turbines intelligence variable blade control system and side
Method, Wind turbines.
Background technique
The control strategy of blower can be divided into two kinds according to rated wind speed: when wind speed is lower than rated wind speed, direct torque
For maximizing power coefficient, the i.e. energy of blower capture；When wind speed is higher than rated wind speed, blower generallys use variable pitch control
System, by adjusting the angle limit mechanical power of blade, thus maintains output power near rated power.Pitch control is
One of the main means of running of wind generating set control switch the significant spies such as frequent, disturbance factor is more with pneumatic nonlinearity, operating condition
Point.
PI controller relies on its simplification and stability, is widely used in the control of fan blade propeller pitch angle.And it is neural
Network and evolution algorithm provide a kind of new thinking for optimization PI gain.In invention, the PI based on RBF neural is controlled
Pitch control device of the device processed as blower uses PSO evolution and calculates to obtain the optimal data collection of Training RBF Neural Network
Method.
Using artificial neural network and evolution algorithm as control method, it is only necessary to system outputs and inputs data, and
The dynamic model of controlled system is not needed.Evolution algorithm is the subset of evolutionary computation, is the branch of artificial intelligence；Artificial neural network
Network is the computing system of machine learning and knowledge token, can calculate the output response of complication system.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of Wind turbines intelligence variable blade control system and methods, wind turbine
Group is designed optimal PI controller, is allowed to greatest extent using prediction of wind speed as the important input of fan master control system
Diminution generator speed measured value and rated value gap.
In order to solve the above technical problems, the present invention provides a kind of Wind turbines intelligence variable blade control system, the system
Include: pitch control device, for obtaining the deviation between the real-time revolving speed of Wind turbines and rated speed, and according to it is described partially
Difference calculates the variable pitch angle reference value that Wind turbines are carried out with pitch control using PI controller, wherein the PI controller
Proportional gain and integral gain are determined by RBF neural according to prediction of wind speed.
As a kind of improvement of technical solution of the present invention, the pitch control device determines the variable pitch angle according to the following formula
Spend reference value:
Wherein, KpFor the proportional gain of the PI controller, KiFor the integral gain of the PI controller, e (t) is real-time
Deviation between revolving speed and rated speed, βrefIt (t) is the variable pitch angle reference value.
As a kind of improvement of technical solution of the present invention, the deviation is determined by following formula:
E (t)=ωg,rated-ωg(t)
Wherein, ωg,ratedFor rated speed, ωgIt (t) is real-time revolving speed, e (t) is the deviation.
As a kind of improvement of technical solution of the present invention, the data that RBF neural is trained are obtained by PSO optimizing
It arrives.
As a kind of improvement of technical solution of the present invention, the PSO optimizing includes: by PSO algorithm, to greater than specified wind
Proportional gain and integral gain under the certain wind speed of speed carry out optimizing, to obtain optimal training dataset.
As a kind of improvement of technical solution of the present invention, by PSO algorithm, under the certain wind speed greater than rated wind speed
Proportional gain and integral gain carry out optimizing, to obtain optimal training dataset, comprising: initialize the ratio under different wind speed
Gain and integral gain；According under different wind speed proportional gain and integral gain, separately design PI controller；Compare different PI
The value of the least cost function of controller；According to the value of the least cost function of different PI controllers, each particle is determined
Optimal location and population optimal location；Update the Position And Velocity of particle in population；Repeat above-mentioned behaviour
Make, until the value of least cost function is sufficiently small.
In addition, the Wind turbines include according to previously described wind turbine the present invention also provides a kind of Wind turbines
The intelligent variable blade control system of group and Wind turbines intelligence moment controlling system.
As a kind of improvement of technical solution of the present invention, in the Wind turbines intelligence moment controlling system, according to as follows
Formula calculating torque reference value:
Wherein, Pg,ratedFor rated power, ωgFor real-time revolving speed.
In addition, the present invention also provides a kind of Wind turbines intelligence pitch control methods, which comprises obtain wind-powered electricity generation
Deviation between the real-time revolving speed and rated speed of unit；According to the deviation, using PI controller calculate to Wind turbines into
The variable pitch angle reference value of row pitch control, wherein the proportional gain of the PI controller and integral gain are by RBF neural
It determines, and the training dataset being trained to the RBF neural is the optimal training dataset by PSO optimizing；Root
When factually wind speed and the PI controller output variable pitch angle reference value, carry out pitch control, with reduce real-time revolving speed with
Deviation between rated speed.
By adopting such a design, the present invention has at least the following advantages:
The present invention determines that blower unifies the PI gain of variable pitch using PSO evolution algorithm and RBF neural, and the method is not
Need founding mathematical models in advance.Using RBF neural tuning PI controller gain when, the air speed value of prediction is as the mind
Input through network, and using the ratio of PI controller and integral gain as the output of RBF neural.It is optimal in order to obtain
Training dataset, the present invention use PSO algorithm, to be greater than rated wind speed certain wind speed under proportional gain and integral gain into
Row optimizing.Trained controller can reduce generator speed measured value and volume by adjusting blade angle to greatest extent
The gap of definite value.
Detailed description of the invention
The above is merely an overview of the technical solutions of the present invention, in order to better understand the technical means of the present invention, below
In conjunction with attached drawing, the present invention is described in further detail with specific embodiment.
Fig. 1 is the structure chart of Wind turbines intelligence variable blade control system；
Fig. 2 is the structure chart of Wind turbines intelligence pitch control model training systems；
Fig. 3 is the flow chart of particle group optimizing process；
Fig. 4 is the structure chart of RBF neural.
Specific embodiment
Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings, it should be understood that preferred reality described herein
Apply example only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention.
The invention proposes the new methods that a kind of wind-driven generator unifies pitch control.In this method, by prediction of wind speed
As the important input of fan master control system, optimal PI controller is designed, allows to reduce generator to greatest extent
The gap of rotary speed measure value and rated value.In order to realize this target, PI controller should provide suitable variable pitch angle reference
Value βref。βrefCalculation formula it is as follows:
Here, KpAnd KiThe ratio and integral gain of PI controller are respectively represented, e (t) can be calculate by the following formula to obtain:
E (t)=ωg,rated-ωg(t)
ωg,ratedAnd ωg(t) rated value and measured value of generator speed are respectively represented.The present invention uses RBF nerve net
The gain of network tuning PI controller, input of the air speed value of prediction as the neural network, and by the ratio and product of PI controller
Divide output of the gain as RBF neural.
Pitch control is activated in full load region, as shown in Figure 1, by the torque calculator in Fig. 1 according to formulaGenerator torque reference value T is calculatedref.According to formulaPass through tune
Whole variable pitch angle reference value βref, the unified pitch control device in the design can provide suitable variable pitch angle beta.Pass through change
Variable pitch angle beta, rotor speed ωr, can finally change generator speed ωg.Therefore, if the controller performance of design is preferable,
Generator speed ωgGenerator rated speed ω should be maintained atg,ratedNear, generator power P at this timegAnd generator torque
TgIt should all be maintained near their rated value.
Unify pitch control device to design the PI of best performance, it is necessary to using optimal training dataset training RBF
Neural network, such RBF neural could provide optimal PI gain.In order to obtain optimal training dataset, the design
Used PSO evolution algorithm, using PSO algorithm, under the certain wind speed for being greater than rated wind speed proportional gain and integral gain
Optimizing is carried out, as shown in Figure 2.Entire searching process by minimizing cost function, i.e. complete by integral absolute error:
Here, e (t) can be calculated by above-mentioned formula.Since in full load region, pitch control device works always,
Therefore integral process is started to work to emulation from same pitch control device and is terminated, and the range of integration of this formula is 0 and tsim。
From the figure 3, it may be seen that PSO calculates the PI of each particle after the position of initialization population scale and particle, speed
Controller gain, and store its IAE value.The optimal location of each particle can be calculated according to IAE value, it can also be at all kinds
Optimal particle is selected in group's particle.Whole process iteration carries out reaching maximum number of iterations until cycle-index, at last
It is secondary be circulated throughout after, optimal particle is also just chosen, in fact, the location information of optimal particle just contains corresponding minimum IAE
The ratio and integral gain of value.
It should be noted that we are not available the best PI gain of the selected variation wind speed of PSO.This is because PSO can only
A pair of of gain (K is provided for constant wind speed (being greater than rated wind speed)pAnd Ki), this be for the constant wind speed to gain it is optimal,
But it is not particularly suited for other wind speed.However we can but obtain one group of optimal data collection by this method.Therefore, Wo Menxu
The optimal PI for wanting an intelligence system based on optimal data collection above, can calculate each wind speed on wind profile increases
Benefit.The present invention has selected RBF neural, as shown in Figure 4.
According to Fig.4, X=[x1,x2,…,xn]TFor input vector,For hidden layer output vector,
Y=[y1,y2,…,ym]TFor output vector.The output of j-th of hidden neuron can be calculated by a Gaussian function:
Here, Cj=[Cj1,Cj2,…,Cjn]TIt is the center vector of j-th of neuron, σ=[σ1,σ2,…,σk]TFor sound stage width
Vector can be determined by experiment.||X-Cj| | it is X-CjThe norm of vector can be calculate by the following formula to obtain:
Therefore, i-th of output neuron of RBF neural:
Here, wpiRepresent p-th of hidden neuron to i-th of output neuron weight.
When the training network, the constant wind speed that optimal data is concentrated is as input, corresponding PI gain as output, tool
Body training method is as follows:
Step1: all weights of random initializtion；
Step2: output vector Y is calculated according to formula (3)；
Step3: the error ε of each output neuron is calculatedi, calculation formula is as follows:
It is the desired output of i-th of output neuron；
Step4: weight is updated using following formula:
Here, n is the number of iterations, and α is learning rate；
Step5: global error ε is calculated according to the following formulaT
Step6: such as reach termination condition (εTLess than worst error), then stop, otherwise returning to Step2；
RBF neural after training, so that it may which it is corresponding to calculate any wind speed in full load region for its general approximation properties
Best PI gain.
The present invention determines that blower unifies the PI gain of variable pitch using PSO evolution algorithm and RBF neural, and the method is not
Need founding mathematical models in advance.Using RBF neural tuning PI controller gain when, the air speed value of prediction is as the mind
Input through network, and using the ratio of PI controller and integral gain as the output of RBF neural.It is optimal in order to obtain
Training dataset, the present invention use PSO algorithm, to be greater than rated wind speed certain wind speed under proportional gain and integral gain into
Row optimizing.Trained controller can reduce generator speed measured value and volume by adjusting blade angle to greatest extent
The gap of definite value.
The above described is only a preferred embodiment of the present invention, be not intended to limit the present invention in any form, this
Field technical staff makes a little simple modification, equivalent variations or modification using the technology contents of the disclosure above, all falls within this hair
In bright protection scope.
Claims (9)
1. a kind of Wind turbines intelligence variable blade control system characterized by comprising
Pitch control device, for obtaining the deviation between the real-time revolving speed of Wind turbines and rated speed, and according to it is described partially
Difference calculates the variable pitch angle reference value that Wind turbines are carried out with pitch control using PI controller, wherein the PI controller
Proportional gain and integral gain are determined by RBF neural according to prediction of wind speed.
2. Wind turbines intelligence variable blade control system according to claim 1, which is characterized in that the pitch control device root
The variable pitch angle reference value is determined according to following formula:
Wherein, KpFor the proportional gain of the PI controller, KiFor the integral gain of the PI controller, e (t) is real-time revolving speed
Deviation between rated speed, βrefIt (t) is the variable pitch angle reference value.
3. Wind turbines intelligence variable blade control system according to claim 2, which is characterized in that the deviation is by following public
Formula determines:
E (t)=ωg,rated-ωg(t)
Wherein, ωg,ratedFor rated speed, ωgIt (t) is real-time revolving speed, e (t) is the deviation.
4. Wind turbines intelligence variable blade control system according to claim 1, which is characterized in that RBF neural into
The data of row training are obtained by PSO optimizing.
5. Wind turbines intelligence variable blade control system according to claim 4, which is characterized in that the PSO optimizing includes:
By PSO algorithm, to the proportional gain and integral gain progress optimizing under the certain wind speed for being greater than rated wind speed, to obtain
Optimal training dataset.
6. Wind turbines intelligence variable blade control system according to claim 5, which is characterized in that by PSO algorithm, to big
Proportional gain and integral gain under the certain wind speed of rated wind speed carry out optimizing, to obtain optimal training dataset, packet
It includes:
Initialize the proportional gain under different wind speed and integral gain；
According under different wind speed proportional gain and integral gain, separately design PI controller；
Compare the value of the least cost function of different PI controllers；
According to the value of the least cost function of different PI controllers, the optimal location and population of each particle are determined
Optimal location；
Update the Position And Velocity of particle in population；
Aforesaid operations are repeated, until the value of least cost function is sufficiently small.
7. a kind of Wind turbines characterized by comprising according to claim 1 to the intelligence of Wind turbines described in 6 any one
Variable blade control system and Wind turbines intelligence moment controlling system.
8. Wind turbines according to claim 7, which is characterized in that in the Wind turbines intelligence moment controlling system,
Calculating torque reference value according to the following formula:
Wherein, Pg,ratedFor rated power, ωgFor real-time revolving speed.
9. a kind of Wind turbines intelligence pitch control method characterized by comprising
Obtain the deviation between the real-time revolving speed and rated speed of Wind turbines；
According to the deviation, the variable pitch angle reference value that Wind turbines are carried out with pitch control is calculated using PI controller, wherein
The proportional gain of the PI controller and integral gain are determined by RBF neural, and are trained to the RBF neural
Training dataset be optimal training dataset by PSO optimizing；
According to the variable pitch angle reference value that real-time wind speed and the PI controller export, pitch control is carried out, it is real-time to reduce
Deviation between revolving speed and rated speed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910115874.4A CN109737008A (en) | 2019-02-15 | 2019-02-15 | Wind turbines intelligence variable blade control system and method, Wind turbines |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910115874.4A CN109737008A (en) | 2019-02-15 | 2019-02-15 | Wind turbines intelligence variable blade control system and method, Wind turbines |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109737008A true CN109737008A (en) | 2019-05-10 |
Family
ID=66367488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910115874.4A Pending CN109737008A (en) | 2019-02-15 | 2019-02-15 | Wind turbines intelligence variable blade control system and method, Wind turbines |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109737008A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110707967A (en) * | 2019-09-10 | 2020-01-17 | 上海航天控制技术研究所 | Self-adaptive control method of brushless direct current motor |
| CN111749847A (en) * | 2020-06-23 | 2020-10-09 | 中国电力科学研究院有限公司 | On-line control method, system and equipment for wind driven generator pitch |
| CN111812983A (en) * | 2020-07-19 | 2020-10-23 | 国网山西省电力公司电力科学研究院 | Wind turbine generator primary frequency modulation load shedding control method based on differential flat active disturbance rejection control |
| CN112855434A (en) * | 2021-01-29 | 2021-05-28 | 三一重能股份有限公司 | Control method and device for wind turbine generator blade, electronic equipment and storage medium |
| CN113027674A (en) * | 2019-12-24 | 2021-06-25 | 北京金风科创风电设备有限公司 | Control method and device of wind generating set |
| CN113255130A (en) * | 2021-05-24 | 2021-08-13 | 中国华能集团清洁能源技术研究院有限公司 | Method and system for evaluating control performance of wind generating set |
| CN113685314A (en) * | 2021-08-24 | 2021-11-23 | 浙江大学 | Pitch control method, system and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140203560A1 (en) * | 2013-01-22 | 2014-07-24 | General Electric Company | Wind turbine and method for adjusting rotor blade pitch angle in wind turbine |
| CN104454347A (en) * | 2014-11-28 | 2015-03-25 | 云南电网公司电力科学研究院 | Method for controlling independent pitch angle of pitch-variable control wind driven generator |
| 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 |
-
2019
- 2019-02-15 CN CN201910115874.4A patent/CN109737008A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140203560A1 (en) * | 2013-01-22 | 2014-07-24 | General Electric Company | Wind turbine and method for adjusting rotor blade pitch angle in wind turbine |
| CN104454347A (en) * | 2014-11-28 | 2015-03-25 | 云南电网公司电力科学研究院 | Method for controlling independent pitch angle of pitch-variable control wind driven generator |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| IMAN POULTANGARI, ET AL: "RBF neural network based PI pitch controller for a class of 5-MW wind turbines using particle swarm optimization algorithm", 《ISA TRANSACTIONS》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110707967A (en) * | 2019-09-10 | 2020-01-17 | 上海航天控制技术研究所 | Self-adaptive control method of brushless direct current motor |
| CN113027674A (en) * | 2019-12-24 | 2021-06-25 | 北京金风科创风电设备有限公司 | Control method and device of wind generating set |
| CN111749847A (en) * | 2020-06-23 | 2020-10-09 | 中国电力科学研究院有限公司 | On-line control method, system and equipment for wind driven generator pitch |
| CN111749847B (en) * | 2020-06-23 | 2021-06-29 | 中国电力科学研究院有限公司 | On-line control method, system and equipment for wind driven generator pitch |
| CN111812983A (en) * | 2020-07-19 | 2020-10-23 | 国网山西省电力公司电力科学研究院 | Wind turbine generator primary frequency modulation load shedding control method based on differential flat active disturbance rejection control |
| CN112855434A (en) * | 2021-01-29 | 2021-05-28 | 三一重能股份有限公司 | Control method and device for wind turbine generator blade, electronic equipment and storage medium |
| CN112855434B (en) * | 2021-01-29 | 2022-04-01 | 三一重能股份有限公司 | Control method and device for wind turbine generator blade, electronic equipment and storage medium |
| CN113255130A (en) * | 2021-05-24 | 2021-08-13 | 中国华能集团清洁能源技术研究院有限公司 | Method and system for evaluating control performance of wind generating set |
| CN113255130B (en) * | 2021-05-24 | 2024-01-23 | 中国华能集团清洁能源技术研究院有限公司 | Method and system for evaluating control performance of wind generating set |
| CN113685314A (en) * | 2021-08-24 | 2021-11-23 | 浙江大学 | Pitch control method, system and readable storage medium |
| CN113685314B (en) * | 2021-08-24 | 2022-06-28 | 浙江大学 | Pitch control method, system and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109737008A (en) | Wind turbines intelligence variable blade control system and method, Wind turbines | |
| CN104595106B (en) | Wind-power generating variable pitch control method based on intensified learning compensation | |
| CN108334672B (en) | Maximum wind energy capturing method of variable-speed wind generating set based on effective wind speed estimation | |
| CN104005909B (en) | The wind generating set pitch control that nonlinear feedforward is combined with fuzzy is away from control method | |
| Bottasso et al. | Aero-servo-elastic modeling and control of wind turbines using finite-element multibody procedures | |
| CN103410660B (en) | Wind-power generating variable pitch Learning Control Method based on support vector machine | |
| CN106786807A (en) | A kind of wind power station active power control method based on Model Predictive Control | |
| CN110374804B (en) | Variable pitch control method based on gradient compensation of depth certainty strategy | |
| CN110566406B (en) | Wind turbine generator set real-time variable pitch robust control system and method based on reinforcement learning | |
| Baheri et al. | Real-time control using Bayesian optimization: A case study in airborne wind energy systems | |
| CN103529698A (en) | Method for distinguishing parameter of power generator speed regulating system | |
| CN105626378A (en) | Large wind turbine unit individual pitch control method based on RBF neural network | |
| CN105888971A (en) | Active load reducing control system and method for large wind turbine blade | |
| CN104500336A (en) | Constant power generalized predictive control method for wind power generator set based on Hammerstein-Wiener model | |
| CN106295001A (en) | The quasi-steady state variable step emulation mode of long time scale be applicable to power system | |
| CN103758699A (en) | Pitch angle control method and pitch angle controller of wind generating set | |
| CN108468622B (en) | Wind turbines blade root load estimation method based on extreme learning machine | |
| CN115333168A (en) | Offshore wind farm field level control strategy based on distributed rolling optimization | |
| CN116306306A (en) | Micro-grid inertia constant estimation method based on African bald-Condition algorithm | |
| Tao et al. | On comparing six optimization algorithms for network-based wind speed forecasting | |
| CN108549207A (en) | A kind of method of Adaptive System of Water-Turbine Engine control parameter | |
| CN115977874A (en) | Wind turbine generator yaw self-adaptive calibration method and system based on laser wind finding radar | |
| CN111749847B (en) | On-line control method, system and equipment for wind driven generator pitch | |
| Karami et al. | Real-time wind direction estimation using machine learning on operational wind farm data | |
| CN110985287B (en) | Indirect rotating speed control method based on width learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190510 |
|
| RJ01 | Rejection of invention patent application after publication |