CN110985290B - Optimal torque control method based on support vector regression - Google Patents
Optimal torque control method based on support vector regression Download PDFInfo
- Publication number
- CN110985290B CN110985290B CN201911224544.5A CN201911224544A CN110985290B CN 110985290 B CN110985290 B CN 110985290B CN 201911224544 A CN201911224544 A CN 201911224544A CN 110985290 B CN110985290 B CN 110985290B
- Authority
- CN
- China
- Prior art keywords
- vector regression
- support vector
- torque control
- wind
- optimal
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000012549 training Methods 0.000 claims abstract description 38
- 238000010606 normalization Methods 0.000 claims abstract description 14
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 6
- 238000006073 displacement reaction Methods 0.000 claims description 6
- 238000010248 power generation Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 8
- 230000007547 defect Effects 0.000 abstract description 2
- 238000007796 conventional method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2260/00—Function
- F05B2260/84—Modelling or simulation
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2270/00—Control
- F05B2270/10—Purpose of the control system
- F05B2270/103—Purpose of the control system to affect the output of the engine
- F05B2270/1032—Torque
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2270/00—Control
- F05B2270/30—Control parameters, e.g. input parameters
- F05B2270/32—Wind speeds
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2270/00—Control
- F05B2270/70—Type of control algorithm
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Control Of Eletrric Generators (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses an optimal torque control method based on support vector regression. The method comprises the steps of obtaining effective wind speed information of a unit in a certain period of time and unit output data related to the effective wind speed in a corresponding period of time, removing correlation in the obtained unit output data, carrying out normalization operation, constructing a training set of support vector regression, determining a support vector regression model by using the training set, obtaining a wind speed estimation model, giving an effective wind speed value on line by the model, and further calculating a rotating speed tracking error and an optimal torque control expression. The method reserves the advantage of simple structure of the traditional optimal torque control algorithm, overcomes the defect of slow convergence rate, can accelerate the convergence rate of the control algorithm to a certain extent, improves the wind energy capture efficiency, is simple and easy to implement, has low implementation cost and few parameters needing debugging, and can improve the unit capacity and increase the benefit of the wind power plant compared with the traditional optimal torque control algorithm.
Description
Technical Field
The invention relates to the technical field of control of wind generating sets, in particular to an optimal torque control method based on support vector regression.
Background
Wind power generation has been rapidly developed worldwide over the past few decades. Wind in nature has strong randomness and indirection, so that the wind power has great unpredictability and volatility, and the wind abandoning and electricity limiting are ubiquitous in the wind power industry, so that the commercial value of wind power generation is to be further improved and mined.
The maximum wind energy capture is one of main control targets of a wind turbine generator and is an important guarantee for maximizing the economic benefit of a wind power plant, in order to achieve the target, an optimal torque control algorithm is generally adopted in the industry at present, the principle of the algorithm is very simple, namely under the condition that the wind speed is assumed to be a fixed value, only the steady state of a system is considered, and the control gain is multiplied by the square of the rotating speed of a generator to be used as a set value of the electromagnetic torque. However, there are two main problems with the optimal torque control algorithm. Firstly, the maximum power coefficient and the optimal tip speed ratio of the wind turbine generator are required to be known for calculating the control gain, although the two key quantities have a nominal value when the wind turbine generator leaves a factory, the maximum power coefficient and the optimal tip speed ratio of the wind turbine generator also change along with the operation of time and the wing shape of the blade changes due to the reasons of abrasion, waste accumulation, blade icing and the like, and the accurate value of the wing shape is difficult to determine, so that the original control gain continuously deviates from the theoretical optimal value, and the wind capturing efficiency of the wind turbine generator system is reduced; secondly, the optimal torque control algorithm does not use wind speed information, and the implementation form of the optimal torque control algorithm does not have an optimal rotating speed tracking error and adjustable parameters which can influence the convergence speed of the optimal rotating speed tracking error, so that the response speed of the algorithm is low under the condition of turbulent wind, and the productivity of a unit can be influenced.
In response to the problems with the optimal torque control algorithm, the scholars have proposed solutions which can be summarized into two categories: a control gain update method and a reduced torque gain method. The control gain updating method mainly solves the first problem of an optimal torque control algorithm, the scheme needs to use a laser radar device to measure effective wind speed so as to calculate wind energy capturing efficiency, and then updates the control gain according to increase and decrease of the wind energy capturing efficiency, so that the control gain is always maintained in a theoretical optimal state, but the practicability of the method is poor because the laser radar wind measuring device is expensive; the method for reducing the rotation speed gain mainly aims at the second problem of the optimal torque control algorithm, the acceleration performance of the unit is accelerated by reducing the control gain, however, the acceleration performance of the unit is accelerated by sacrificing the deceleration performance of the unit, and when the reduction proportion of the control gain is not properly selected, the wind capturing efficiency of the unit is not increased or decreased.
Aiming at the problems in a control gain updating method and a torque gain reducing method, the method uses an effective wind speed estimation method based on support vector regression to replace an expensive radar wind measuring device, adds noise in a training set of a wind speed estimation model so as to improve the robustness of a wind speed estimation algorithm and further obtain an optimal rotating speed estimation value, compensates the torque gain by introducing a proportion term of a rotating speed tracking error, increases the convergence speed of the algorithm to a certain extent, and improves the wind energy capturing efficiency of a unit.
Disclosure of Invention
In order to improve the wind energy capture efficiency of an optimal torque control algorithm and solve the problems of high implementation cost and difficult parameter selection of the existing optimal torque control method, the invention provides the optimal torque control method which is low in implementation cost, simple in control parameter debugging and good in robustness, the construction and operation and maintenance cost of a wind power plant can be reduced, the convergence performance of the algorithm is accelerated to a certain extent, the unit capacity is improved, and the economic benefit of the wind power plant is increased.
The technical scheme adopted by the invention for solving the technical problems is as follows: an optimal torque control method based on support vector regression, the method comprising the steps of:
the method comprises the steps that (1) effective wind speed information of a unit in a certain period of time is obtained and is marked as V ', Gaussian noise with the mean value of 0 and the variance of 0.1 is added to V', V is obtained and is a training target set of a support vector regression model, unit output data relevant to the effective wind speed information in the corresponding period of time is obtained, correlation in the obtained unit output data is removed, and data with the correlation removed are obtained;
step (2) carrying out normalization processing on the data obtained in the step (1) after the correlation is removed, marking as X ', adding Gaussian noise with the mean value of 0 and the variance of 0.05 into each column of X', obtaining a training feature set X supporting vector regression, wherein the training feature set X and a training target set V jointly form a training set supporting vector regression, and adding noise into the training set supporting vector regression model is helpful to improve the robustness of the wind speed estimation algorithm;
selecting a kernel function, determining punishment parameters and kernel function parameters of the support vector regression model by using a firework algorithm, and training by using the training set in the step (2) to obtain the support vector regression model;
when the wind power generation set is used on line, normalization processing is carried out on the output data of the set after the correlation is removed, the output data are input into the support vector regression model obtained through training in the step (3), and an effective wind speed estimation value is obtained through calculation;
and (6) obtaining a tracking error e according to the step (5) to obtain an optimal torque control expression:
wherein is TgElectromagnetic torque set point, ωgIs the generator speed, kp> 0 is a constant control parameter selected by the user, CpmaxIs the optimal wind energy utilization coefficient, ngIs the gear box drive ratio, λoptThe optimum tip speed ratio of the unit is obtained, R is the radius of the wind wheel, and rho is the air density.
Further, in step (1), effective wind speed information of the unit in a certain period of time is obtained by a lidar wind measuring device, and a SCADA system is used to record unit output data X '═ X' (i, j) ], i ═ 1., l, j ═ 1., 8, which is associated with the effective wind speed information in a corresponding period of time, where X '(i, j) is a sampled output of the SCADA system, and a row component expression of X' is:
x'(i,:)＝[ωr,ωg,Tem,Pe,afa,vfa,xfa,Ra]
wherein, ω isrIs the rotational speed of the wind wheel, omegagIs the generator speed, TemIs an electromagnetic torque, PeIs the generated power, afaIs the tower fore-aft acceleration, vfaIs the tower fore-aft velocity, xfaIs a tower fore-and-aft displacement, RaIs the angular displacement of the wind wheel.
Further, in the step (1), a PCA algorithm is adopted to remove the correlation in the acquired unit output data, and the specific steps include: performing decentralized processing on the unit output data, namely subtracting respective mean values from each line of data of X'; calculating a covariance matrix; calculating an eigenvalue and an eigenvector of the covariance matrix; sorting the eigenvectors in columns according to the eigenvalues from big to small, and taking the first 4 columns to form a matrix P; the data X' is projected onto the matrix P, and the data X ″, from which the correlation is removed, is obtained as X ″ (i, j).
Further, in the step (2), the normalization processing specifically includes:
where X "(: j) represents the column component in X", μ (j) and σ (j) are the mean and standard deviation, respectively, of X "(: j), and X (: j) constitutes the column component in the training feature set X that supports vector regression.
Further, in the step (3), the kernel function supporting vector regression selects sigmoid function as follows
Where γ and r are hyper-parameters to be selected, x represents a certain support vector, and z represents the input features of the support vector regression model.
Further, in the step (3), the fitness function of the firework algorithm is selected as the mean square error of the support vector regression model for the training set.
Further, in the step (4), the effective wind speed estimation value
The expression of (a) is:
wherein f issvrRepresenting a trained support vector regression model, xnewThe unit real-time output is processed by PCA decorrelation and normalization.
Further, in the step (5), the tracking error e of the wind wheel rotating speed is as follows:
wherein, ω isrIs the rotational speed of the wind wheel,
is an optimal wind wheel speed estimate, λoptThe optimal tip speed ratio of the unit is shown, and R is the radius of the wind wheel.
The invention has the beneficial effects that: the effective wind speed estimation is carried out by using the support vector regression, so that the use of a laser radar wind measuring device is avoided, the system cost is reduced, and the robustness of a wind speed estimation algorithm is improved by the noise processing on the model training set; by introducing the proportion term of the rotating speed tracking error into the traditional optimal torque control algorithm, the convergence rate of the algorithm is accelerated to a certain extent, and the wind energy capture efficiency is improved under the condition that the basic form of the optimal torque control algorithm is not changed. The optimal torque control method based on support vector regression provided by the invention reserves the advantage of simple structure of the traditional optimal torque control algorithm, overcomes the defect of low convergence rate, is simple and easy to implement, has low implementation cost and few parameters needing debugging, and can improve the unit productivity and increase the economic benefit of a wind power plant compared with the traditional optimal torque control algorithm.
Drawings
FIG. 1 is a block diagram of the method control of the present invention;
FIG. 2 is a comparison graph of the real wind speed value and the estimated wind speed value;
FIG. 3 is a plot of wind speed estimation error;
FIG. 4 is a flow chart of the method of the present invention;
FIG. 5 is a graph comparing the power generated by the method of the present invention with that of the conventional method;
FIG. 6 is a graph comparing electromagnetic torque of the proposed method and the conventional method;
fig. 7 is a comparison graph of the rotor speed of the method of the present invention compared to the conventional method.
Detailed Description
The invention is described in further detail below with reference to the figures and specific examples.
The invention provides an optimal torque control method based on support vector regression, which comprises the following steps:
step 1, in order to obtain a training sample of a wind speed estimation model, the pitch angle of a wind turbine generator is maintained to be 0 degree, and the maximum wind energy capture is realized by using an optimal torque control algorithm. In the normal operation process of the unit, a laser radar wind measuring device is used for obtaining effective wind speed information of the unit within a certain period of time, the effective wind speed information is recorded as V ', Gaussian noise with the mean value of 0 and the variance of 0.1 is added to the V', V is obtained, the V is a support vector regression training target set, and meanwhile, an SCADA system is used for recording unit output data X 'which is [ X' (i, j) ], i is 1, l, j is 1, 8, wherein X '(i, j) is primary sampling output of the SCADA system, and a row component expression of X' is as follows:
x'(i,:)＝[ωr,ωg,Tem,Pe,afa,vfa,xfa,Ra]
wherein, ω isrIs the rotational speed of the wind wheel, omegagIs the generator speed, TemIs an electromagnetic torque, PeIs the generated power, afaIs the tower fore-aft acceleration, vfaIs the tower fore-aft velocity, xfaIs a tower fore-and-aft displacement, RaIs the angular displacement of the wind wheel.
Further, in order to remove the correlation in the unit output data X 'and improve the accuracy of effective wind speed estimation, a PCA algorithm is used to perform dimension reduction on the output data X', the data is subjected to decentralization (that is, the mean value of each column of data of X 'is subtracted), a covariance matrix is calculated, eigenvalues and eigenvectors of the covariance matrix are calculated, the eigenvectors are sorted from large to small according to the eigenvalues, the first 4 columns are taken to form a matrix P, and the data X' is projected into the matrix P, so that the data X ″ -X ″ (i:) with the correlation removed is obtained.
Step 2, carrying out normalization processing on the unit output data X' obtained in the step 1, wherein the specific operation is as follows:
where X "(: j) denotes the column component in X", and μ (j) and σ (j) are the mean and standard deviation of X "(: j), respectively. Gaussian noise with the mean value of 0 and the variance of 0.05 is added into X (: j), the X (: j) after noise addition forms column components in a training feature set X of the support vector regression model, the training feature set X and a training target set V jointly form a training set of the support vector regression, and the noise is added into the training set of the support vector regression model to help improve the robustness of the wind speed estimation algorithm.
And 3, selecting a kernel function, determining a penalty parameter and a kernel function parameter of the support vector regression by using a firework algorithm, and training by using the training set in the step 1 to obtain a support vector regression model. The kernel function selects a sigmoid function as follows
Where γ and r are the hyper-parameters that need to be selected. And selecting a fitness function of the firework algorithm as a mean square error of the support vector regression algorithm on a training set.
Wherein f issvrRepresenting a trained support vector regression model, xnewThe unit real-time output is processed by PCA decorrelation and normalization.
wherein, ω isrIs the rotational speed of the wind wheel, λoptIs the optimal tip speed ratio of the unit, R is the radius of the wind wheel,
and the estimated value of the optimal wind wheel rotating speed is obtained.
Step 6, obtaining the tracking error e according to the step 5, and obtaining the following optimal torque control form
Wherein is TgElectromagnetic torque set value, kp> 0 is a constant control parameter selected by the user, CpmaxIs the optimal wind energy utilization coefficient, ngIs the gearbox ratio. By introducing a proportional link of a tracking error of the rotating speed of the wind wheel, the convergence speed of the algorithm is accelerated to a certain extent (the acceleration and deceleration performance of a unit can be accelerated at the same time), the time for adjusting the optimal rotating speed of the optimal torque control algorithm is shortened, and finally the wind energy capturing efficiency of the algorithm is improved.
Examples
In the embodiment, GH Bladed wind power development software is used for verifying the effectiveness of the method provided by the invention. To illustrate the inventive novelty, a comparison is made with the conventional optimal torque control method as follows
Wherein, TgOTCIs the electromagnetic torque value, k, given by the optimal torque control algorithmoptIs a control parameter, ωgIs the rotating speed of the generator, rho is 1.225Kg/m3Is the air density, R is 38.5m is the wind wheel radius, Cpmax0.482 is the maximum wind energy capture coefficient, λopt8.5 is the optimum tip speed ratio, ng104.494 is the gear ratio of the gearbox.
FIG. 1 shows a control block diagram of the method of the present invention. After the real-time output of the unit is subjected to PCA decorrelation and normalization operation, the real-time output of the unit is input into a wind speed estimation model based on support vector regression to obtain a wind speed estimation value; calculating to obtain an optimal wind wheel rotating speed estimation value, and further calculating to obtain a wind wheel rotating speed tracking error; the proportion term of the tracking error of the rotating speed of the wind wheel is used for compensating the original optimal torque control parameter, the convergence rate of the algorithm is accelerated to a certain extent, the unit capacity is improved, and the economic benefit of the wind power plant is increased.
FIG. 2 shows a comparison of the true and estimated values of the effective wind speed. The wind speed estimated value basically has the variation trend of the wind speed real value, and the variation trend of the wind speed estimated value can improve the dynamic performance of the optimal torque control method and improve the productivity of the unit. Calculated, the wind speed estimate was 6.51% MAPE and 0.1863m MSE2/s2。
As shown in fig. 3, the wind speed estimation error map is shown. The estimation error is basically between +/-1 m/s, and the effectiveness of the wind speed estimation method is illustrated. FIG. 4 shows a flow chart of the method of the present invention. Firstly, acquiring relevant output data of a unit, performing data preprocessing including PCA decorrelation and normalization, and constructing a training set supporting vector regression; secondly, selecting a kernel function, determining a penalty parameter and a kernel function parameter of support vector regression by combining a firework algorithm and a training set to obtain an effective wind speed estimation model, and giving the size of a wind speed estimation value on line by using the wind speed estimation model; and finally, calculating a tracking error of the rotating speed, and further providing an electromagnetic torque control signal expression.
Fig. 5 is a graph comparing the generated power of the method of the present invention with that of the conventional method. The smoothness degree of the power obtained by the method is similar to that of the traditional method, so that the method cannot cause the shaking of the generated power and cannot influence the power generation quality. According to calculation, the method disclosed by the invention has the advantages that the productivity is improved by 0.77% compared with that of the traditional method, and the yield is improved by 0.77% due to the fact that the generating capacity base number of the actual wind power plant is very large.
Fig. 5 is a graph showing the electromagnetic torque comparison between the method of the present invention and the conventional method. It can be seen that the torque signal of the method is smoother, and therefore, the method does not bring about the increase of the load of the transmission chain of the unit.
Fig. 6 shows a comparison of the rotor speed of the proposed method and the conventional method. Therefore, the wind wheel rotating speed signal obtained by the method is smooth, and the severe vibration of the wind wheel rotating speed cannot be brought, so that the service life of the unit cannot be influenced.
The above-described embodiments are intended to illustrate rather than to limit the invention, and any modifications and variations of the present invention are within the spirit of the invention and the scope of the appended claims.
Claims (8)
1. An optimal torque control method based on support vector regression, characterized in that the method comprises the following steps:
the method comprises the steps that (1) effective wind speed information of a unit in a certain period of time is obtained and is marked as V ', Gaussian noise with the mean value of 0 and the variance of 0.1 is added to V', V is obtained and is a training target set of a support vector regression model, unit output data relevant to the effective wind speed information in the corresponding period of time is obtained, correlation in the obtained unit output data is removed, and data with the correlation removed are obtained;
step (2) carrying out normalization processing on the data obtained in the step (1) after the correlation is removed, marking the data as X ', adding Gaussian noise with the mean value of 0 and the variance of 0.05 into each column of the X' to obtain a training feature set X supporting vector regression, wherein the training feature set X and a training target set V jointly form a training set supporting vector regression, and adding noise into the training set supporting vector regression model is beneficial to improving the robustness of the wind speed estimation algorithm;
selecting a kernel function, determining punishment parameters and kernel function parameters of the support vector regression model by using a firework algorithm, and training by using the training set in the step (2) to obtain the support vector regression model;
when the wind power generation set is used on line, normalization processing is carried out on the output data of the set after the correlation is removed, the output data are input into the support vector regression model obtained through training in the step (3), and an effective wind speed estimation value is obtained through calculation;
step 5, obtaining an optimal wind wheel rotating speed estimated value of the wind wheel of the unit according to the effective wind speed estimated value obtained in the step 4, and further calculating to obtain a wind wheel rotating speed tracking error;
and (6) obtaining a tracking error e according to the step (5) to obtain an optimal torque control expression:
wherein is TgElectromagnetic torque set point, ωgIs the generator speed, kp> 0 is a constant control parameter selected by the user, CpmaxIs the optimal wind energy utilization coefficient, ngIs the gear box drive ratio, λoptThe optimum tip speed ratio of the unit is obtained, R is the radius of the wind wheel, and rho is the air density.
2. The optimal torque control method based on support vector regression according to claim 1, wherein in step (1), the effective wind speed information of the unit in a certain period of time is obtained by a lidar wind measuring device, and simultaneously, a SCADA system is used for recording unit output data X ' (i, j) ], i 1, l, j 1, 8 related to the effective wind speed information in a corresponding period of time, wherein X ' (i, j) is a once-sampled output of the SCADA system, and the row component expression of X ' is as follows:
x'(i,:)＝[ωr,ωg,Tem,Pe,afa,vfa,xfa,Ra]
wherein, ω isrIs the rotational speed of the wind wheel, omegagIs the generator speed, TemIs an electromagnetic torque, PeIs the generated power, afaIs the tower fore-aft acceleration, vfaIs the tower fore-aft velocity, xfaIs a tower fore-and-aft displacement, RaIs the angular displacement of the wind wheel.
3. The support vector regression-based optimal torque control method according to claim 1, wherein in the step (1), a PCA algorithm is adopted to remove the correlation in the acquired unit output data, and the specific steps include: performing decentralized processing on the unit output data, namely subtracting respective mean values from each line of data of X'; calculating a covariance matrix; calculating an eigenvalue and an eigenvector of the covariance matrix; sorting the eigenvectors in columns according to the eigenvalues from big to small, and taking the first 4 columns to form a matrix P; the data X' is projected onto the matrix P, and the data X ″, from which the correlation is removed, is obtained as X ″ (i, j).
4. The optimal torque control method based on support vector regression according to claim 1, wherein in the step (2), the specific operation of the normalization process is:
wherein X "(: j) represents the column component in X", μ (j) and σ (j) are the mean and standard deviation, respectively, of X "(: j), and X (: j) constitutes the column component in the training feature set X that supports vector regression.
5. The support vector regression-based optimal torque control method according to claim 1, wherein in the step (3), the kernel function of support vector regression selects sigmoid function as follows
Where γ and r are hyper-parameters to be selected, x represents a certain support vector, and z represents the input features of the support vector regression model.
6. The support vector regression-based optimal torque control method according to claim 1, wherein in the step (3), the fitness function of the firework algorithm is selected as the mean square error of the support vector regression model for the training set.
7. The SVM regression-based optimal torque control method as claimed in claim 1, wherein in the step (4), the effective wind speed estimate is
The expression of (a) is:
wherein f issvrRepresenting a trained support vector regression model, xnewThe unit real-time output is processed by PCA decorrelation and normalization.
8. The optimal torque control method based on support vector regression according to claim 1, wherein in step (5), the tracking error e of the rotor speed is:
wherein, ω isrIs the rotational speed of the wind wheel,
is an optimal wind wheel speed estimate, λoptThe optimal tip speed ratio of the unit is shown, and R is the radius of the wind wheel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911224544.5A CN110985290B (en) | 2019-12-04 | 2019-12-04 | Optimal torque control method based on support vector regression |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911224544.5A CN110985290B (en) | 2019-12-04 | 2019-12-04 | Optimal torque control method based on support vector regression |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110985290A CN110985290A (en) | 2020-04-10 |
| CN110985290B true CN110985290B (en) | 2022-02-11 |
Family
ID=70089872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911224544.5A Active CN110985290B (en) | 2019-12-04 | 2019-12-04 | Optimal torque control method based on support vector regression |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110985290B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103437955A (en) * | 2013-08-13 | 2013-12-11 | 华北电力大学（保定） | Maximum power tracking device for mini permanent magnetic direct drive wind power generation system and control method |
| CN104234934A (en) * | 2014-08-06 | 2014-12-24 | 东北大学 | Wind power generator rotating speed control method |
| CN104675629A (en) * | 2014-12-03 | 2015-06-03 | 浙江大学 | Maximum wind energy capturing method of variable-speed wind generating sets |
| CN104806450A (en) * | 2015-03-25 | 2015-07-29 | 华北电力大学（保定） | Universal gravitation neural network based wind power system MPPT control method |
| CN106529706A (en) * | 2016-10-25 | 2017-03-22 | 国家电网公司 | Support-vector-machine-regression-based method for predicting wind speed of wind power plant |
| CN106979126A (en) * | 2017-04-12 | 2017-07-25 | 浙江大学 | Wind power generating set high wind speed section effective wind speed method of estimation based on SVR |
| CN108334672A (en) * | 2018-01-14 | 2018-07-27 | 浙江大学 | Variable Speed Wind Power Generator maximal wind-energy capture method based on effective wind speed estimation |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10330081B2 (en) * | 2017-02-07 | 2019-06-25 | International Business Machines Corporation | Reducing curtailment of wind power generation |
-
2019
- 2019-12-04 CN CN201911224544.5A patent/CN110985290B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103437955A (en) * | 2013-08-13 | 2013-12-11 | 华北电力大学（保定） | Maximum power tracking device for mini permanent magnetic direct drive wind power generation system and control method |
| CN104234934A (en) * | 2014-08-06 | 2014-12-24 | 东北大学 | Wind power generator rotating speed control method |
| CN104675629A (en) * | 2014-12-03 | 2015-06-03 | 浙江大学 | Maximum wind energy capturing method of variable-speed wind generating sets |
| CN104806450A (en) * | 2015-03-25 | 2015-07-29 | 华北电力大学（保定） | Universal gravitation neural network based wind power system MPPT control method |
| CN106529706A (en) * | 2016-10-25 | 2017-03-22 | 国家电网公司 | Support-vector-machine-regression-based method for predicting wind speed of wind power plant |
| CN106979126A (en) * | 2017-04-12 | 2017-07-25 | 浙江大学 | Wind power generating set high wind speed section effective wind speed method of estimation based on SVR |
| CN108334672A (en) * | 2018-01-14 | 2018-07-27 | 浙江大学 | Variable Speed Wind Power Generator maximal wind-energy capture method based on effective wind speed estimation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110985290A (en) | 2020-04-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108334672B (en) | Maximum wind energy capturing method of variable-speed wind generating set based on effective wind speed estimation | |
| CN110761947B (en) | Yaw calibration method and system for wind turbine generator | |
| CN106979126B (en) | Wind power generating set high wind speed section effective wind speed estimation method based on SVR | |
| CN111079343B (en) | Wind turbine generator effective wind speed estimation method based on width learning | |
| EP3791060B1 (en) | Wind turbine control method | |
| CN111120205B (en) | Wind power plant regionalization control method based on laser radar | |
| CN110454329A (en) | A kind of Wind turbines award setting method | |
| CN107045574B (en) | SVR-based effective wind speed estimation method for low wind speed section of wind generating set | |
| CN111075647B (en) | ELM-based maximum wind energy capture method for variable-speed wind turbine generator | |
| CN106374465B (en) | Short-term wind power forecast method based on GSA-LSSVM model | |
| CN110365053B (en) | Short-term wind power prediction method based on delay optimization strategy | |
| CN113935247B (en) | Partition virtual inertia estimation method considering wind speed randomness and correlation | |
| CN108985490A (en) | Wind-driven generator power curve modification method based on the fitting of sliding window characteristic | |
| CN115807734A (en) | Offshore wind farm level cooperative control strategy based on wake flow tracking | |
| CN110991701A (en) | Wind power plant fan wind speed prediction method and system based on data fusion | |
| Schlipf et al. | Systems engineering for lidar-assisted control: a sequential approach | |
| CN110966144B (en) | BLS-based intelligent constant power control method for wind turbine generator | |
| CN113294297B (en) | Variable weight adjusting method for wind turbine generator nonlinear model prediction torque control | |
| CN110985290B (en) | Optimal torque control method based on support vector regression | |
| CN115977874A (en) | Wind turbine generator yaw self-adaptive calibration method and system based on laser wind finding radar | |
| CN110985287B (en) | Indirect rotating speed control method based on width learning | |
| CN110985289B (en) | SVR and SMC based MPPT method with preset performance for wind turbine generator | |
| US11885305B2 (en) | Method of determining the wind speed in the rotor plane of a wind turbine | |
| CN110889780B (en) | Wind turbine generator system performance-guaranteeing maximum wind energy capturing method based on BLS and double-layer SMC | |
| CN110985286B (en) | Wind turbine generator pitch angle control method based on ELM |
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 |