CN113236507B - Yaw static error diagnosis method and system for wind turbine generator - Google Patents
Yaw static error diagnosis method and system for wind turbine generator Download PDFInfo
- Publication number
- CN113236507B CN113236507B CN202110593768.4A CN202110593768A CN113236507B CN 113236507 B CN113236507 B CN 113236507B CN 202110593768 A CN202110593768 A CN 202110593768A CN 113236507 B CN113236507 B CN 113236507B
- Authority
- CN
- China
- Prior art keywords
- yaw
- static error
- wind
- yaw static
- turbine generator
- 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
- 230000003068 static effect Effects 0.000 title claims abstract description 134
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000003745 diagnosis Methods 0.000 title claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 238000007781 pre-processing Methods 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 19
- 230000002159 abnormal effect Effects 0.000 claims description 24
- 238000005259 measurement Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000002405 diagnostic procedure Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 5
- 238000002939 conjugate gradient method Methods 0.000 claims description 4
- 230000006698 induction Effects 0.000 claims description 4
- 238000012821 model calculation Methods 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 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
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- 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
- F03D7/02—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor
- F03D7/022—Adjusting aerodynamic properties of the blades
-
- 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
- F03D7/02—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor
- F03D7/04—Automatic control; Regulation
- F03D7/042—Automatic control; Regulation by means of an electrical or electronic controller
- F03D7/043—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic
- F03D7/046—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic with learning or adaptive control, e.g. self-tuning, fuzzy logic or neural network
-
- 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
- F05B2270/329—Azimuth or yaw angle
-
- 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)
- Physics & Mathematics (AREA)
- Fluid Mechanics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Wind Motors (AREA)
Abstract
The embodiment of the invention discloses a method and a system for diagnosing yaw static errors of a wind turbine generator, wherein the method comprises the following steps: preprocessing wind power characteristic data and wind power plant environment data collected under the measured wind speed; according to a preset regression model, calculating the preprocessed wind power characteristic data and wind power plant environment data to obtain power parameters corresponding to the yaw static errors of the wind turbine generator, so as to determine a yaw static error interval under the measured and calculated wind speed; and processing a plurality of measured and calculated wind speed yaw static error intervals in the yaw control stage to serve as the yaw static error of the current wind turbine generator. The method realizes the rapid diagnosis of the yaw static error of the wind turbine generator through a machine learning algorithm; the yaw static error is diagnosed according to the data of the whole yaw control stage, and the diagnosis result is more reliable by considering different wind conditions; and the interval where the yaw static error is located is obtained, and the universality and reference value of the control of the wind turbine generator are improved.
Description
Technical Field
The invention relates to the technical field of wind power plant power prediction, in particular to a wind turbine generator yaw static error diagnosis method based on a combined prediction theory.
Background
Wind energy is a renewable clean energy, and under the current global energy crisis and environmental crisis, wind power generation is generally valued and popularized.
Due to the limitation of wind resources in China, the annual average wind speed is low, the wind turbine generator operates in a yaw control stage most of time, and the yaw control technology and the sensor technology are not substantially developed in engineering application, so that the yaw error of the wind turbine generator is not eliminated, and the power generation performance of the wind turbine generator is seriously influenced.
The existing large number of control strategies and algorithms are characterized by dynamic errors when measuring and calculating the yaw errors, and actually, the influence of the yaw static errors is 2-3 times that of the dynamic errors, the yaw static errors are seriously influenced,
thus, there is a need for a solution that can compensate for the effects of yaw dynamic errors by correcting the yaw static errors.
Disclosure of Invention
In view of this, the present invention provides a method and a system for diagnosing a yaw static error of a wind turbine generator, so as to correct the yaw static error to compensate the yaw dynamic error.
A wind turbine generator yaw static error diagnosis method comprises the following steps:
preprocessing wind power characteristic data and wind power plant environment data collected under the measured wind speed;
according to a preset regression model, calculating the preprocessed wind power characteristic data and wind power plant environment data to obtain power parameters corresponding to the yaw static error of the wind turbine generator so as to determine a yaw static error interval under the measured wind speed;
and processing a plurality of measured and calculated wind speed yaw static error intervals in the yaw control stage to serve as the yaw static error of the current wind turbine generator.
Preferably, the preprocessing of the wind power characteristic data and the wind power plant environment data collected under the wind speed measurement and calculation includes:
determining the relationship between the air density and the current temperature and the current altitude according to a preset first algorithm;
and correcting the output power value of the wind turbine generator according to a second algorithm.
Preferably, the diagnostic method further comprises:
and converting the output power value of the wind turbine generator into a wind energy utilization coefficient.
Preferably, the preprocessing of the wind power characteristic data and the wind power plant environment data collected under the wind speed measurement and calculation includes:
filtering concentrated wind speed and power abnormal data;
clearing abnormal values of equipment operation data;
and deleting the extreme yaw angle value.
Preferably, the diagnostic method further comprises:
and (4) carrying out sample-based abnormity judgment on the concentrated wind speed and power, equipment operation data and a yaw angle by adopting a SCiForest algorithm.
Preferably, the diagnostic method further comprises:
constructing a sparse Gaussian regression model, comprising:
dividing a sample data set into a training set and a test set according to a preset proportion;
and training the induction input to approximate to actual distribution by a conjugate gradient method to obtain a sparse Gaussian regression model.
Preferably, the processing of the plurality of estimated wind speed and yaw static error intervals in the yaw control phase includes:
calculating the mean value and the variance of the power coefficient corresponding to the yaw angle by using a sparse Gaussian regression model under a plurality of measured and calculated wind speeds;
taking the average value as the output of a regression model to obtain a first yaw static error;
c with 95% confidence p The value is used as a second yaw static error obtained by the output of the regression model;
determining a yaw static error interval under a certain measurement wind speed according to the first yaw static error and the second yaw static error;
the method comprises the following steps of processing a plurality of wind speed and yaw static error measuring and calculating intervals in a yaw control stage, and specifically comprises the following steps:
and taking a union set of the yaw static error intervals obtained under the wind speeds measured and calculated as the interval of the yaw static error of the wind turbine generator.
A wind turbine generator yaw static error diagnostic system comprises:
the preprocessing module is used for preprocessing wind power characteristic data and wind power plant environment data collected under the measured wind speed;
the model calculation module is used for calculating the preprocessed wind power characteristic data and the wind power plant environment data according to a preset regression model to obtain power parameters corresponding to the yaw static error of the wind turbine generator so as to determine a yaw static error interval under the measured and calculated wind speed;
and the yaw static error interval processing module is used for processing a plurality of yaw static error intervals for measuring and calculating wind speed in a yaw control stage as the yaw static error of the current wind turbine generator.
Preferably, the preprocessing module is specifically configured to:
determining the relation between the air density and the current temperature and the current altitude according to a preset first algorithm;
correcting the output power value of the wind turbine generator according to a second algorithm;
and the number of the first and second groups,
filtering concentrated wind speed and power abnormal data;
clearing abnormal values of equipment operation data;
and deleting the extreme value of the yaw angle.
Preferably, the yaw static error interval processing module is specifically configured to:
calculating the mean value and the variance of the power coefficient corresponding to the yaw angle by using a sparse Gaussian regression model under a plurality of measured wind speeds;
taking the average value as the output of a regression model to obtain a first yaw static error;
c with 95% confidence p The value is used as a second yaw static error obtained by the output of the regression model;
determining a yaw static error interval under a certain measurement wind speed according to the first yaw static error and the second yaw static error;
and taking a union set of the yaw static error intervals obtained under the wind speed measurement and calculation as the interval of the yaw static error of the wind turbine generator.
According to the technical scheme, the method and the system for diagnosing the yaw static error of the wind turbine generator set, provided by the embodiment of the invention, establish the sparse Gaussian regression model for the preprocessed data at different wind speeds, and obtain the average value and the variance of the power coefficient corresponding to the yaw angle. And respectively taking the power coefficients corresponding to the mean value and the 95% confidence coefficient as the output of the model, determining a yaw static error interval under the wind speed, and taking the union of the diagnosis results of different wind speeds in the yaw control stage as the yaw static error of the wind turbine generator. According to the method, an accurate model can be established by using less data through a machine learning algorithm so as to diagnose the yaw static error, and the fast diagnosis of the yaw static error of the wind turbine generator is realized; the yaw static error is diagnosed according to the data of the whole yaw control stage, and the diagnosis result is more reliable by considering different wind conditions; and the interval where the yaw static error is located is obtained, and the universality and the reference value of the control of the wind turbine generator are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for diagnosing yaw static errors of a wind turbine generator according to an embodiment of the present invention;
FIG. 2 is a flow chart of a preprocessing method in a wind turbine yaw static error diagnosis method disclosed by the embodiment of the invention;
FIG. 3 is a preprocessing flow chart of a method for diagnosing yaw static errors of a wind turbine generator, disclosed by an embodiment of the invention;
FIG. 4 is a flowchart of a model calculation method in a method for diagnosing yaw static errors of a wind turbine generator system according to an embodiment of the present invention;
FIG. 5 is a flow chart of a method for diagnosing yaw static errors of a wind turbine generator according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a wind turbine generator yaw static error diagnosis system disclosed in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
The embodiment of the invention discloses a method and a system for diagnosing yaw static errors of a wind turbine generator, which aim to respond to the short-term wind speed change condition of a complex and variable wind power plant and improve the prediction accuracy.
FIG. 1 shows a wind turbine yaw static error diagnosis method, which includes:
s11, preprocessing the collected wind power characteristic data and wind power plant environment data under the measured wind speed;
referring to fig. 2, a flow chart of the correction loop flow in the preprocessing is shown:
in the yaw control phase of the wind turbine, the stall performance of the blades depends only on the wind speed, which can be adjusted as long as an aerodynamically determined wind speed is reached. However, since the regulation conditions are determined by the power under standard air, the actual output power of the wind turbine will be affected. Therefore, in diagnosing the yaw static error, it is necessary to correct the measurement data in consideration of the influence of the natural environment such as the actual temperature, the altitude, and the air density. And correcting the output power of the wind turbine generator according to the ambient temperature and the altitude data.
S21, determining the relation between the air density and the current temperature and the current altitude according to a preset first algorithm;
the relationship between air density and temperature and altitude can be obtained (3) from the krebs equation of equation (1) and the relationship between air pressure and altitude of equation (2).
BV＝nRT (1)
Wherein B is pressure; v is the volume of gas; n is the amount of material of the gas; t is the thermodynamic temperature of the system; r is a proportionality constant having a value of 8.31441J/(mol. K).
B＝e 5.25885×In(288.15-0.0065h)-18.2573 (2)
Where h is the altitude at the hub.
Where ρ is the air density at the hub; m is the molar mass of air.
And S22, correcting the output power value of the wind turbine generator according to a second algorithm.
The expression for power correction is shown in equation (4):
wherein P is the actual measured power; p c Is the correction power; rho s Is the standard air density, and the value is 1.205Kg/m 3 。；p s Is a standard atmospheric pressure; t is t a Is the actual ambient temperature; t is t s Is the standard ambient temperature (20 ℃).
Preferably, the diagnostic method further comprises:
and S23, converting the output power value of the wind turbine generator into a wind energy utilization coefficient.
Because the output power of the wind turbine generator set changes greatly under the same wind speed, in order to reduce modeling errors, the power is converted into a wind energy utilization coefficient G according to the formula (5) according to the international standard IEC61400-12-1 p 。
Where A is the rotor swept area.
Fig. 3 shows the abnormal data screening and detecting process in the preprocessing, and since the wind turbine generator operating data often contains abnormal data due to the influence of factors such as measurement, transmission, control, wind abandoning and electricity limiting during the actual operation of the wind turbine generator, the operating data cannot accurately reflect the actual operation state of the wind turbine generator. Therefore, the operation data needs to be preprocessed, and abnormal data needs to be accurately identified and cleared.
Firstly, by an intuitive method, some abnormal data can be intuitively identified and screened by observing a time sequence diagram and a scatter distribution diagram of wind turbine generator operation data, as shown in figure 3,
s31, filtering the concentrated wind speed and power abnormal data;
processing data with continuous and unchangeable wind speed and power in a data set, wherein the abnormal data are caused by factors such as wind abandonment and electricity limitation
S32, clearing abnormal values of the equipment operation data;
clearing abnormal values caused by communication equipment, measurement equipment, unplanned downtime and the like, wherein the data are generally stacked at the bottom of a power curve;
and S33, deleting the extreme value of the yaw angle.
And controlling the yaw angle to be +/-50 degrees, and clearing the extreme value of the yaw angle.
Secondly, a SCiForest algorithm is used for carrying out sample-based abnormal judgment on the concentrated wind speed and power, the equipment operation data and the yaw angle, but the specific algorithm is adopted for judging the abnormal data, and the method is not limited. The SCiForest is an improvement of an isolated forest, and the defect that the isolated forest can only identify global anomalies is overcome. Because the wind power data is label-free data, whether a certain data is abnormal or not can not be directly obtained. The SCiForest conforms to the characteristic, does not directly judge whether the data are abnormal, but provides an abnormal probability for each data. In addition, the method does not need to calculate any density and distance and has low calculation complexity. Wherein the abnormality score of each data is represented by the formula (6):
wherein the average path length of the tree is
The sum h (i) ═ ln (i) + 0.5772156649.
After the abnormality score is calculated for each sample, a threshold value needs to be set for determination. If the abnormal score is smaller than the threshold value, the data point is regarded as normal data; the anomaly score is greater than a threshold, and the data point is considered anomalous data.
S12, calculating the preprocessed wind power characteristic data and the wind power plant environment data according to a preset regression model to obtain power parameters corresponding to the yaw static errors of the wind turbine generator so as to determine a yaw static error interval under the measured and calculated wind speed;
referring to fig. 4, the present invention employs machine learning to construct a sparse gaussian regression model, comprising:
the method comprises the steps of establishing data of a selective yaw control stage for training by using a sparse Gaussian regression model (analyzing the relationship of a yaw angle power coefficient by using a sparse Gaussian process regression model SGPR, and better predicting the probability distribution of an output result), carrying out binning processing on a data set according to a certain wind speed step length, establishing a regression model in each bin, and determining a yaw angle and a power coefficient.
S41, dividing the sample data set into training set and testing set according to preset proportion;
dividing the data in each box into a training set and a test set according to the proportion of 7:3, and applying the test set to a training model to obtain a result shown as a formula (7)
Wherein Z is an inducement input, the inducement input being M data points selected from the N data points of the training set (N > M),
and S42, training the induction input to be close to actual distribution through a conjugate gradient method to obtain a sparse Gaussian regression model.
Optimizing the position of the induction input by a conjugate gradient method to enable the position to be close to actual distribution; k (-) is a kernel function, in the present invention a Squared Explicit (SE) covariance function is chosen; i is an identity matrix; k MN ＝K(Z，X)；K MM ＝K(Z，Z)；K NN ＝K(X，X)；K NM ＝K(X，Z)。
And S13, processing the yaw static error intervals of the wind speed measured and calculated in the yaw control stage to be used as the yaw static error of the current wind turbine generator.
Referring to fig. 5, a flow of processing a plurality of reckoned wind speed yaw static error intervals for a yaw control phase is shown, comprising:
after an SGPR model is established in each subdata set, according to the obtained theta-C p Curve, theoretical C p The maximum point corresponds to θ being 0 °. However, theta is not zero when the yaw static error exists, and the value of theta at the moment is taken as the yaw static error value at the wind speed.
S51, calculating the average value and the variance of the power coefficient corresponding to the yaw angle by using a sparse Gaussian regression model under a plurality of measured wind speeds;
s52, taking the average value as the output of the regression model to obtain a first yaw static error;
according to the obtained result of the regression model, the yaw static error obtained by taking the average value as the output of the regression model is
S53, C with 95% confidence p The value is used as a second yaw static error obtained by the output of the regression model;
c with 95% confidence p The value obtained as the output of the regression model is the yaw static error
S54, determining a yaw static error interval under a certain measured wind speed according to the first yaw static error and the second yaw static error;
interval in which static error of yaw angle is located
Therefore, a plurality of wind speed and yaw static error intervals are measured and calculated in the yaw control stage, and the method is specifically realized as follows:
and taking a union set of the yaw static error intervals obtained under the wind speeds measured and calculated as the interval of the yaw static error of the wind turbine generator.
And taking the union of the intervals obtained by different boxes as the interval where the yaw static error of the wind turbine generator is located.
Wherein, theta zsp And the yaw static error of the wind turbine generator is shown, and n is the data binning number.
Referring to fig. 6, a wind turbine yaw static error diagnostic system is shown, comprising:
the preprocessing module 61 is used for preprocessing wind power characteristic data and wind power plant environment data collected under the measured wind speed;
the model calculation module 62 is used for calculating the preprocessed wind power characteristic data and the wind power plant environment data according to a preset regression model to obtain power parameters corresponding to the yaw static error of the wind turbine generator, so as to determine a yaw static error interval under the measured and calculated wind speed;
preferably, the preprocessing module 61 is specifically configured to:
determining the relation between the air density and the current temperature and the current altitude according to a preset first algorithm;
correcting the output power value of the wind turbine generator according to a second algorithm;
and the number of the first and second groups,
filtering concentrated wind speed and power abnormal data;
clearing abnormal values of equipment operation data;
and deleting the extreme value of the yaw angle.
And the yaw static error interval processing module 63 is used for processing a plurality of measured wind speed yaw static error intervals in the yaw control stage as the yaw static error of the current wind turbine generator.
Preferably, the yaw static error interval processing module 63 is specifically configured to:
calculating the mean value and the variance of the power coefficient corresponding to the yaw angle by using a sparse Gaussian regression model under a plurality of measured wind speeds;
taking the average value as the output of a regression model to obtain a first yaw static error;
c with 95% confidence p The value is used as a second yaw static error obtained by the output of the regression model;
determining a yaw static error interval under a certain measurement wind speed according to the first yaw static error and the second yaw static error;
and taking a union set of the yaw static error intervals obtained under the wind speed measurement and calculation as the interval of the yaw static error of the wind turbine generator.
It is to be noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In summary, the following steps:
according to the method and the system for diagnosing the yaw static error of the wind turbine generator, a sparse Gaussian regression model is established for preprocessed data at different wind speeds, and the average value and the variance of power coefficients corresponding to a yaw angle are obtained. And respectively taking the power coefficients corresponding to the mean value and the 95% confidence coefficient as the output of the model, determining the yaw static error interval under the wind speed, and taking the union set of the diagnosis results of different wind speeds in the yaw control stage as the yaw static error of the wind turbine generator. According to the method, the accurate model can be established by using less data through the machine learning algorithm so as to diagnose the yaw static error, and the rapid diagnosis of the yaw static error of the wind turbine generator is realized; the yaw static error is diagnosed according to the data of the whole yaw control stage, and the diagnosis result is more reliable by considering different wind conditions; and the interval where the yaw static error is located is obtained, and the universality and the reference value of the control of the wind turbine generator are improved.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
Those of skill in the art would understand that information, messages, and signals may be represented using any of a variety of different technologies and techniques. For example, the messages and information mentioned in the above description can be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or any combination thereof.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the components and steps of the various examples have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the embodiments. Thus, the present embodiments are not intended to be limited to the embodiments shown herein but are to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A wind turbine generator yaw static error diagnosis method is characterized by comprising the following steps:
preprocessing wind power characteristic data and wind power plant environment data collected under the measured wind speed;
according to a preset regression model, calculating the preprocessed wind power characteristic data and wind power plant environment data to obtain power parameters corresponding to the yaw static errors of the wind turbine generator, so as to determine a yaw static error interval under the measured and calculated wind speed;
processing a plurality of measured and calculated wind speed and yaw static error intervals in a yaw control stage as a yaw static error of the current wind turbine generator, wherein the processing of the plurality of measured and calculated wind speed and yaw static error intervals in the yaw control stage comprises the following steps:
calculating the mean value and the variance of the power coefficient corresponding to the yaw angle by using a sparse Gaussian regression model under a plurality of measured and calculated wind speeds;
taking the average value as the output of a regression model to obtain a first yaw static error;
taking the power coefficient corresponding to the 95% confidence coefficient as the output of the regression model to obtain a second yaw static error;
determining a yaw static error interval under a certain measurement wind speed according to the first yaw static error and the second yaw static error;
and taking a union set of the yaw static error intervals obtained under the wind speed measurement and calculation as the interval of the yaw static error of the wind turbine generator.
2. The method for diagnosing the yaw static error of the wind turbine generator set according to claim 1, wherein the preprocessing of the wind power characteristic data and the wind farm environment data collected under the measured wind speed comprises:
determining the relation between the air density and the current temperature and the current altitude according to a preset first algorithm;
and correcting the output power value of the wind turbine generator according to a second algorithm.
3. The wind turbine yaw static error diagnostic method according to claim 2, further comprising:
and converting the output power value of the wind turbine generator into a power coefficient to form a wind energy utilization coefficient.
4. The method for diagnosing the yaw static error of the wind turbine generator set according to claim 1, wherein the preprocessing is performed on the wind power characteristic data and the wind farm environment data collected under the measured wind speed, and further comprising:
filtering concentrated wind speed and power abnormal data;
clearing abnormal values of equipment operation data;
and deleting the extreme value of the yaw angle.
5. The wind turbine generator yaw static error diagnostic method of claim 4, further comprising:
and (4) carrying out sample-based abnormity judgment on the concentrated wind speed and power, equipment operation data and a yaw angle by adopting a SCiForest algorithm.
6. The wind turbine generator yaw static error diagnostic method of claim 1, further comprising:
constructing a sparse Gaussian regression model, comprising:
dividing a sample data set into a training set and a test set according to a preset proportion;
and training the induction input to approximate to actual distribution by a conjugate gradient method to obtain a sparse Gaussian regression model.
7. A wind turbine yaw static error diagnostic system comprising:
the preprocessing module is used for preprocessing wind power characteristic data and wind power field environment data collected under the measured wind speed;
the model calculation module is used for calculating the preprocessed wind power characteristic data and the wind power plant environment data according to a preset regression model to obtain power parameters corresponding to the yaw static errors of the wind turbine generator so as to determine a yaw static error interval under the measured and calculated wind speed;
the yaw static error interval processing module is used for processing a plurality of measured and calculated wind speed yaw static error intervals in a yaw control stage as the yaw static errors of the current wind turbine generator, wherein the yaw static error interval processing module is specifically configured as follows:
calculating the mean value and the variance of the power coefficient corresponding to the yaw angle by using a sparse Gaussian regression model under a plurality of measured wind speeds;
taking the average value as the output of a regression model to obtain a first yaw static error;
taking the corresponding power coefficient with the 95% confidence coefficient as the output of the regression model to obtain a second yaw static error;
determining a yaw static error interval under a certain measurement wind speed according to the first yaw static error and the second yaw static error;
and taking a union set of the yaw static error intervals obtained under the wind speed measurement and calculation as the interval of the yaw static error of the wind turbine generator.
8. The wind turbine yaw static error diagnostic system of claim 7, wherein the preprocessing module is specifically configured to:
determining the relationship between the air density and the current temperature and the current altitude according to a preset first algorithm;
correcting the output power value of the wind turbine generator according to a second algorithm;
and (c) a second step of,
filtering concentrated wind speed and power abnormal data;
clearing abnormal values of equipment operation data;
and deleting the extreme yaw angle value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110593768.4A CN113236507B (en) | 2021-05-28 | 2021-05-28 | Yaw static error diagnosis method and system for wind turbine generator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110593768.4A CN113236507B (en) | 2021-05-28 | 2021-05-28 | Yaw static error diagnosis method and system for wind turbine generator |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113236507A CN113236507A (en) | 2021-08-10 |
| CN113236507B true CN113236507B (en) | 2022-08-19 |
Family
ID=77135553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110593768.4A Active CN113236507B (en) | 2021-05-28 | 2021-05-28 | Yaw static error diagnosis method and system for wind turbine generator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113236507B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113931808A (en) * | 2021-10-25 | 2022-01-14 | 中国华能集团清洁能源技术研究院有限公司 | Method and device for diagnosing yaw error of wind turbine generator |
| CN114483485B (en) * | 2022-02-24 | 2024-07-16 | 兰州大学 | Method for improving wind speed prediction of Nudging wind farm observation data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104481804A (en) * | 2014-12-05 | 2015-04-01 | 北京金风科创风电设备有限公司 | Wind power generator group wind correction control method, device and system |
| CN106355512A (en) * | 2016-08-26 | 2017-01-25 | 华北电力大学 | Power curve fitting method of wind turbine generator based on optimizing maximum value of probability density |
| WO2018014825A1 (en) * | 2016-07-21 | 2018-01-25 | 浙江运达风电股份有限公司 | Method and device for automatically calibrating wind alignment error of wind power generation unit |
| CN108488038A (en) * | 2018-03-27 | 2018-09-04 | 中南大学 | A kind of Yaw control method of wind power generating set |
| CN109488528A (en) * | 2018-11-23 | 2019-03-19 | 华润电力技术研究院有限公司 | A kind of method of adjustment and device of fan yaw system |
| CN110094310A (en) * | 2019-05-13 | 2019-08-06 | 北京天泽智云科技有限公司 | A method of identification wind driven generator yaw is not positive to wind |
| CN110761947A (en) * | 2019-11-15 | 2020-02-07 | 华北电力大学 | Yaw calibration method and system for wind turbine generator |
| WO2020097944A1 (en) * | 2018-11-18 | 2020-05-22 | 浙江大学 | Real power curve-based method for discriminating and compensating yaw error inherent deviation of wind turbine generator set |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104314757B (en) * | 2014-10-15 | 2017-03-29 | 国电联合动力技术有限公司 | A kind of wind generating set yaw control method and system |
| CN108547736A (en) * | 2018-03-27 | 2018-09-18 | 中南大学 | The Yaw control method of wind speed and direction prediction technique and wind power generating set |
| DK3807529T3 (en) * | 2018-09-17 | 2024-03-25 | American Superconductor Corp | Yaw autocalibration for a wind turbine generator |
| CN109667727B (en) * | 2018-11-18 | 2020-01-10 | 浙江大学 | Wind turbine generator yaw error inherent deviation identification and compensation method based on power curve analysis |
-
2021
- 2021-05-28 CN CN202110593768.4A patent/CN113236507B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104481804A (en) * | 2014-12-05 | 2015-04-01 | 北京金风科创风电设备有限公司 | Wind power generator group wind correction control method, device and system |
| WO2018014825A1 (en) * | 2016-07-21 | 2018-01-25 | 浙江运达风电股份有限公司 | Method and device for automatically calibrating wind alignment error of wind power generation unit |
| CN106355512A (en) * | 2016-08-26 | 2017-01-25 | 华北电力大学 | Power curve fitting method of wind turbine generator based on optimizing maximum value of probability density |
| CN108488038A (en) * | 2018-03-27 | 2018-09-04 | 中南大学 | A kind of Yaw control method of wind power generating set |
| WO2020097944A1 (en) * | 2018-11-18 | 2020-05-22 | 浙江大学 | Real power curve-based method for discriminating and compensating yaw error inherent deviation of wind turbine generator set |
| CN109488528A (en) * | 2018-11-23 | 2019-03-19 | 华润电力技术研究院有限公司 | A kind of method of adjustment and device of fan yaw system |
| CN110094310A (en) * | 2019-05-13 | 2019-08-06 | 北京天泽智云科技有限公司 | A method of identification wind driven generator yaw is not positive to wind |
| CN110761947A (en) * | 2019-11-15 | 2020-02-07 | 华北电力大学 | Yaw calibration method and system for wind turbine generator |
Non-Patent Citations (1)
| Title |
|---|
| 风电机组偏航校正分析方法研究;张伟等;《华电技术》;20170425(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113236507A (en) | 2021-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11401913B2 (en) | Yaw calibration method and system for wind turbine | |
| CN113236507B (en) | Yaw static error diagnosis method and system for wind turbine generator | |
| CN106321368B (en) | Marine wind electric field wake losses measurement method based on operation blower SCADA data | |
| Gao et al. | Data-driven yaw misalignment correction for utility-scale wind turbines | |
| CN117688497B (en) | Data processing method for marine wind power wake interference based on backward trajectory model | |
| CA3035871A1 (en) | Method and device for monitoring a status of at least one wind turbine and computer program product | |
| Mehlan et al. | Rotor imbalance detection and diagnosis in floating wind turbines by means of drivetrain condition monitoring | |
| Song et al. | Data and decision level fusion-based crack detection for compressor blade using acoustic and vibration signal | |
| CN113612237A (en) | Method for positioning resonance-induced subsynchronous oscillation source in offshore wind farm | |
| Bilendo et al. | A normal behavior model based on power curve and stacked regressions for condition monitoring of wind turbines | |
| Xing et al. | Detection of magnitude and position of rotor aerodynamic imbalance of wind turbines using Convolutional Neural Network | |
| Iungo et al. | Machine-learning identification of the variability of mean velocity and turbulence intensity for wakes generated by onshore wind turbines: Cluster analysis of wind LiDAR measurements | |
| CN113343562B (en) | Fan power prediction method and system based on hybrid modeling strategy | |
| CN114320770B (en) | Method and device for measuring effective wind speed of wind turbine generator | |
| Shipley et al. | Techniques for the determination of local dynamic pressure and angle of attack on a horizontal axis wind turbine | |
| CN109976300A (en) | The performance indicator detection method and computer storage medium of servo-system | |
| CN111997833A (en) | Wind turbine generator set composite intelligent pitch control method based on laser wind measurement feedforward | |
| US20230213560A1 (en) | Calculating energy loss during an outage | |
| D'Amico et al. | Influence of atmospheric conditions on measured infrasound from wind turbines | |
| Bao et al. | Iterative modeling of wind turbine power curve based on least‐square B‐spline approximation | |
| Movsessian et al. | Adaptive feature selection for enhancing blade damage diagnosis on an operational wind turbine | |
| Hernández et al. | Wind resource assessment in the surroundings of San Luis Potosi, Mexico | |
| Peco Chacon et al. | Support vector machine and K-fold cross-validation to detect false alarms in wind turbines | |
| CN117189509B (en) | Lightning stroke fault detection method for offshore wind turbine | |
| Astolfi et al. | Assessing the effects of anemometer systematic errors on wind generators performance by data-driven techniques |
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 |