CN114909264A - Load prediction method, fatigue life estimation method, load reduction control method and system - Google Patents
Load prediction method, fatigue life estimation method, load reduction control method and system Download PDFInfo
- Publication number
- CN114909264A CN114909264A CN202210594690.2A CN202210594690A CN114909264A CN 114909264 A CN114909264 A CN 114909264A CN 202210594690 A CN202210594690 A CN 202210594690A CN 114909264 A CN114909264 A CN 114909264A
- Authority
- CN
- China
- Prior art keywords
- wind turbine
- data
- load
- target
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 84
- 230000009467 reduction Effects 0.000 title claims description 9
- 238000005259 measurement Methods 0.000 claims abstract description 16
- 230000004927 fusion Effects 0.000 claims abstract description 12
- 238000006073 displacement reaction Methods 0.000 claims description 35
- 230000001133 acceleration Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 12
- 238000005452 bending Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 2
- 230000007246 mechanism Effects 0.000 abstract description 4
- 230000004044 response Effects 0.000 abstract description 4
- 238000004088 simulation Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 239000012080 ambient air Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000010977 unit operation 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
- F03D7/028—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor controlling wind motor output power
-
- 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
-
- 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
- F05B2270/304—Spool rotational speed
-
- 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
-
- 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
- F05B2270/335—Output power or torque
-
- 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)
- Wind Motors (AREA)
- Control Of Eletrric Generators (AREA)
Abstract
The application provides a load prediction method, a fatigue life estimation method, a load shedding control method and a load shedding control system. The wind turbine load prediction method comprises the following steps: and obtaining model output data of the detectable variable of the target part by using a dynamic model corresponding to the target part of the wind turbine generator, wherein the dynamic model is constructed according to the detectable variable. And fusing the model output data and the measurement data of the detectable variable to obtain fused data. And determining the target load of the target part according to the fusion data. Therefore, the target load is predicted by using the dynamic model, the dynamic response mechanism of the wind turbine generator is considered, and the prediction result is reliable.
Description
Technical Field
The application relates to the technical field of wind power, in particular to a load prediction method, a fatigue life estimation method, a load shedding control method and a system for a wind turbine generator.
Background
With the large-scale development of the wind turbine generator, the load of the whole wind turbine generator continuously rises. Load is a key factor influencing the operating life of the wind turbine generator, so that it is particularly important to realize real-time prediction of the load of the wind turbine generator.
At present, people adopt a big data machine learning mode, model training is carried out based on software load simulation data, and a load prediction model for online load prediction based on unit operation state data is constructed. However, the accuracy of the prediction model is difficult to verify and the load prediction result is unreliable in the prediction model based on machine learning.
Disclosure of Invention
An object of the embodiments of the present application is to provide a load prediction method, a fatigue life estimation method, a load shedding control method and system, and a computer-readable storage medium, which enable a load prediction result to be reliable.
The embodiment of the application provides a wind turbine load prediction method, which comprises the following steps:
obtaining model output data of a detectable variable of a target part by using a dynamic model corresponding to the target part of the wind turbine generator, wherein the dynamic model is constructed according to the detectable variable;
fusing the model output data and the measurement data of the detectable variable to obtain fused data;
and determining the target load of the target part according to the fusion data.
Optionally, the input of the dynamic model comprises a rotor torque;
the method comprises the following steps:
acquiring a pitch angle and a blade tip speed ratio;
obtaining the wind wheel torque by utilizing a two-dimensional lookup table of wind wheel torque, the pitch angle and the blade tip speed ratio according to the pitch angle and the blade tip speed ratio;
the method for obtaining the model output data of the detectable variable of the target part by using the dynamic model corresponding to the target part of the wind turbine generator set comprises the following steps:
and inputting the wind wheel torque into the dynamic model to obtain the model output data.
Optionally, the input of the dynamic model comprises a wind turbine thrust;
the method comprises the following steps:
acquiring a pitch angle and a blade tip speed ratio;
obtaining the wind wheel thrust by utilizing a two-dimensional lookup table of the wind wheel thrust, the pitch angle and the blade tip speed ratio according to the pitch angle and the blade tip speed ratio;
the method for obtaining the model output data of the detectable variable of the target part by using the dynamic model corresponding to the target part of the wind turbine generator set comprises the following steps:
and inputting the wind wheel thrust into the dynamic model to obtain the model output data.
Optionally, the state quantity of the dynamic model includes a cross-sectional displacement and a cross-sectional velocity of the target site;
the method for obtaining the model output data of the detectable variable of the target part by using the dynamic model corresponding to the target part of the wind turbine generator set comprises the following steps:
obtaining current data of the section displacement and current data of the section speed at the current moment according to the data of the section displacement and the data of the section speed at the last moment of the dynamic model;
and obtaining the model output data by using the dynamic model comprising the current data of the section displacement and the current data of the section velocity.
Optionally, the determining the target load of the target portion according to the fusion data includes:
determining the gain of the dynamic model at the current moment according to the fusion data and the model output data at the current moment;
determining an estimated value of the section displacement at the current moment according to the current data of the section displacement at the current moment and the gain at the current moment;
determining a target load of the target portion according to the estimated value of the section displacement at the current moment.
Optionally, the detectable variable includes at least one of generator speed, generator torque, blade pitch angle, blade root bending moment, blade tip acceleration, and nacelle acceleration.
Optionally, the fusing the model output data and the measurement data of the detectable variable to obtain fused data includes:
and fusing the model output data and the measurement data of the detectable variable by using a Kalman filtering algorithm to obtain fused data.
The embodiment of the application provides a fatigue life estimation method for a wind turbine generator, which comprises the following steps:
and determining the fatigue life of the target part by using the target load determined by the wind turbine load prediction method in any embodiment.
The embodiment of the application provides a load reduction control method for a wind turbine generator, which comprises the following steps:
the wind turbine load prediction method according to any one of the embodiments controls the load reduction operation of the wind turbine when the determined target load is larger than the load set value of the target position.
The embodiment of the application provides a wind turbine load prediction system, includes:
a memory and a processor;
wherein the memory is used for storing a computer program;
the processor is configured to execute the computer program to implement the wind turbine load prediction method according to any one of the above embodiments, the fatigue life estimation method for a wind turbine according to any one of the above embodiments, or the load shedding control method for a wind turbine according to any one of the above embodiments.
An embodiment of the present application provides a computer-readable storage medium, configured to store a computer program, where the computer program, when executed by a processor, implements a wind turbine load prediction method according to any one of the above embodiments, a fatigue life estimation method for a wind turbine according to any one of the above embodiments, or a wind turbine load shedding control method according to any one of the above embodiments.
According to the load prediction method provided by the embodiment of the application, the dynamic model of the target part of the wind turbine generator is utilized, the model output data of the detectable variable is obtained based on the dynamic model, the model output data and the measurement data of the detectable variable are fused to obtain the fused data, and then the target load of the target part is determined. The target load is predicted by using the dynamic model, the dynamic response mechanism of the wind turbine generator is considered, and the prediction result is reliable.
Drawings
Fig. 1 is a schematic perspective view of a wind turbine generator shown in an embodiment of the present application;
FIG. 2 is a schematic flow chart illustrating a wind turbine load prediction method according to an embodiment of the present application;
FIG. 3 is a schematic flow chart illustrating steps of determining a rotor thrust of the wind turbine in the wind turbine load prediction method of FIG. 2;
FIG. 4 is a schematic flow chart illustrating steps of determining rotor torque of the wind turbine shown in FIG. 2 according to the wind turbine load prediction method;
FIG. 5 is a schematic flow chart illustrating the steps of determining model output data for a dynamical model of the wind turbine load prediction method of FIG. 2;
fig. 6 is a schematic flow chart illustrating a step of determining a target load of a target portion in the wind turbine load prediction method shown in fig. 2.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. Unless defined otherwise, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The terms "first," "second," and the like, as used in the description and in the claims, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. Also, the use of the terms "a" or "an" and the like do not denote a limitation of quantity, but rather denote the presence of at least one. "plurality" or "a number" means two or more. The word "comprising" or "comprises", and the like, means that the element or item listed as preceding "comprising" or "includes" covers the element or item listed as following "comprising" or "includes" and its equivalents, and does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
The wind turbine load prediction method of the embodiment of the application comprises the following steps: and obtaining model output data of the detectable variables of the target part by using a dynamic model corresponding to the target part of the wind turbine generator, wherein the dynamic model is constructed according to the detectable variables. Fusing the output data of the model and the measurement data of the detectable variable to obtain fused data; and determining the target load of the target part according to the fusion data.
According to the wind turbine load prediction method of some embodiments of the application, a dynamic model of a target portion of a wind turbine is utilized, model output data of a detectable variable is obtained based on the dynamic model, the model output data and measurement data of the detectable variable are fused to obtain fused data, and then the target load of the target portion is determined. The target load is predicted by using the dynamic model, the dynamic response mechanism of the wind turbine generator is considered, and the prediction result is reliable.
Wind power generation is to convert kinetic energy of wind into mechanical kinetic energy and then convert the mechanical kinetic energy into electrical kinetic energy. Wind power generation devices are called wind generating sets or wind turbines. The application provides a wind turbine load prediction method, a fatigue life estimation method, a load shedding control method and system and a readable storage medium. The present application will be described in detail below with reference to the accompanying drawings.
Fig. 1 is a wind turbine generator 10 according to an embodiment of the present application, including: a tower 20, a nacelle 21, a wind rotor 22. Wherein a nacelle 21 is mounted on top of a tower 20, the tower 20 supporting the nacelle 21. A wind rotor 22 is mounted to nacelle 21, and wind rotor 22 includes a hub 25 and blades 26 mounted to hub 25. In the present embodiment, the rotor 22 is mounted at the front of the nacelle 21, and in other embodiments, the rotor 22 may be mounted at the rear of the nacelle 21. The number of blades 26 is three, and in other examples, the number of blades 26 can be set according to actual conditions.
It is understood that the rotor 22 is a component for converting kinetic energy of wind into mechanical energy, and when the wind blows to the blades 26, the blades 26 generate aerodynamic force to drive the rotor 22 to rotate. A generator connected with the wind wheel 22 can be arranged in the nacelle 21, and the rotation of the wind wheel 22 drives a rotor inside the generator to rotate, so as to generate electricity.
Referring to fig. 2, an embodiment of the present application provides a load prediction method applied to a wind turbine 10, where the load prediction method includes steps S101 to S103.
In step S101, model output data of a detectable variable at a target portion is obtained by using a dynamic model corresponding to the target portion of the wind turbine generator, where the dynamic model is constructed according to the detectable variable.
In some embodiments, the target portion of the wind turbine may be a key portion of the wind turbine, and the selection of the key portion may be performed specifically according to a structural characteristic of the wind turbine, and the target portion may include one or more of a wind wheel, a generator rotor, a tower, and a nacelle. The corresponding kinetic model of the target site may thus include: the model comprises a wind wheel model corresponding to a wind wheel, a rotor model corresponding to a generator rotor, a tower model corresponding to a tower and a cabin model corresponding to a cabin.
The kinetic model is constructed from the detectable variables. In some embodiments, the detectable variable may be an operating state parameter of the wind turbine, which may include generator speed, generator torque, blade pitch angle, blade root bending moment, blade tip acceleration, and nacelle acceleration. Different dynamic models may be constructed based on different detectable variables, and in some embodiments, a wind turbine model may be constructed based on one or more of blade pitch angle, blade root bending moment, and blade tip acceleration; the tower model may be constructed based on nacelle acceleration; the generator rotor model may be constructed based on generator speed and/or generator torque.
A dynamical model may be used to represent the force versus motion acting on an object. In some embodiments, the dynamical model may be a physical function of the input quantities, the state quantities and the output quantities. The input quantity may be an external force acting on the dynamic model, and the state quantity and the output quantity may be used to represent the motion of the target portion. Because the external force of the wind turbine generator is generated by wind power, the wind power acts on the wind wheel and is transmitted to each part of the wind turbine generator, and therefore the external force acting on different target parts can be expressed by using the force acting on the wind wheel. For example, the input of the tower model may be the wind wheel thrust, wherein, referring to fig. 3, the wind wheel thrust may be obtained by steps S201 to S202.
In step S201, a pitch angle and a tip speed ratio are acquired.
Most of the existing wind power units adopt variable pitch control, and power is adjusted by adjusting the windward angle of blades. The pitch angle refers to an included angle between an airfoil chord line at the top end of the blade and a rotating plane, and can be directly obtained through a pitch control system. The tip speed ratio is a very important parameter for expressing the characteristics of the wind turbine, and represents the ratio of the tip linear speed of the wind turbine blade to the wind speed.
In step S202, the wind turbine thrust is obtained by using the two-dimensional lookup table of the wind turbine thrust, the pitch angle, and the tip speed ratio according to the pitch angle and the tip speed ratio.
The two-dimensional lookup table of the wind wheel thrust, the pitch angle and the blade tip speed ratio can be obtained through simulation of the wind turbine generator under different pitch angles and blade tip speed ratios. A unit model of the wind turbine generator is established in simulation software of a computer, and then the unit model runs under different pitch angles and blade tip speed ratios to obtain data of wind wheel thrust of the wind turbine generator. And establishing a two-dimensional lookup table for obtaining the wind wheel thrust, the pitch angle and the blade tip speed ratio by using each group of pitch angle and blade tip speed ratio and the corresponding wind wheel thrust. Because of wind uncertainty, aerodynamic force acting on a wind wheel is not changed linearly, so that the wind wheel thrust is obtained by adopting a two-dimensional lookup table of the wind wheel thrust, the pitch angle and the blade tip speed ratio, and the influence of nonlinear factors of the aerodynamic force can be avoided. In other embodiments, the rotor thrust may also be determined from the power of the wind turbine, the pitch angle, the ambient wind speed, and the ambient air density.
In some embodiments, the input to the rotor model includes rotor torque, see fig. 4, which may be obtained using steps S301-S302.
In step S301, a pitch angle and a tip speed ratio are acquired;
the method for obtaining the pitch angle and the tip speed ratio is the same as the method in step S201, and is not described again.
In step S302, in step S202, the wind wheel torque is obtained by using the two-dimensional lookup table of the wind wheel torque, the pitch angle, and the tip speed ratio according to the pitch angle and the tip speed ratio.
The two-dimensional lookup table of the wind wheel torque, the pitch angle and the blade tip speed ratio can be obtained through simulation of the wind turbine generator under different pitch angles and blade tip speed ratios. A unit model of the wind turbine generator is established in simulation software of a computer, and then the unit model runs under different pitch angles and blade tip speed ratios to obtain data of wind wheel torque of the wind turbine generator. And establishing a two-dimensional lookup table of the wind wheel torque, the pitch angle and the blade tip speed ratio by using each group of pitch angle and blade tip speed ratio and the corresponding wind wheel torque. Because of wind uncertainty, aerodynamic force acting on the wind wheel is not changed linearly, and further wind wheel torque for driving the wind wheel to rotate is not changed linearly, so that the wind wheel torque is obtained by adopting a two-dimensional lookup table of the wind wheel torque, the pitch angle and the tip speed ratio, and the influence of nonlinear factors of the aerodynamic force can be avoided.
In one embodiment, the input quantities of the rotor model may comprise rotor torque and rotor thrust, wherein rotor thrust and rotor torque may be obtained in the manner already described above.
The state quantity of the dynamic model may be a physical quantity describing the state of the target portion, which changes with time under the action of the input quantity, and the state quantity changes accordingly. In some embodiments, the state quantity may include a cross-sectional displacement and a cross-sectional velocity, wherein the cross-sectional displacement and the cross-sectional velocity are used to represent the displacement of the cross-section and the velocity of the cross-section inside the target site. In other embodiments, the state quantities may also include momentum, kinetic energy, angular velocity, angular momentum, pressure, temperature, volume, potential energy, and the like.
The output quantity of the kinetic model may be a detectable variable, and the data corresponding to the output quantity is the model output data. In some embodiments, the model output data of the tower model may be a nacelle acceleration value; the model output data of the rotor model may be generator speed and generator torque; the output data of the wind wheel model can be blade pitch angle, blade root bending moment and blade tip acceleration.
Referring to FIG. 5, in some embodiments, the model output data may be obtained by the following method steps S401-S402.
In step S401, the current data of the cross-sectional displacement and the current data of the cross-sectional velocity at the current time are obtained from the data of the cross-sectional displacement and the data of the cross-sectional velocity at the previous time on the dynamic model. It can be understood that the current data of the cross section displacement at the current moment can be obtained by the data of the cross section displacement at the previous moment and the data of the speed of the cross section displacement at the previous moment, wherein the speed of the cross section is multiplied by the time to be the displacement of the cross section, the speed of the cross section can be changed under the participation of the input quantity, and the data of the cross section displacement at the previous moment and the data of the cross section displacement are equal to the current data of the cross section displacement at the current moment; the current data of the section velocity at the current moment can be obtained by the section velocity at the previous moment and the input quantity of the dynamic model.
In step S402, a dynamic model including the current data of the section displacement and the current data of the section velocity is used to obtain model output data. In some alternative embodiments, the model output data may be data corresponding to a model output quantity, and the model output data is determined based on the current data of the section displacement and the current data of the section velocity.
With continued reference to FIG. 2, in step S102, the model output data is fused with the measured data of the detectable variable to obtain fused data. Wherein the output of the kinetic model corresponds to the detectable variable. In some embodiments, the measurement data of the above-mentioned detectable variables may be obtained by: the rotating speed and the torque of the generator can be obtained through rotating speed and torque sensors, the blade pitch angle can be obtained through blade pitch angle parameters of a main control system of the wind turbine generator, blade root bending moment can be obtained by arranging a bending moment sensor at the root of the blade, blade tip acceleration can be obtained by arranging an acceleration sensor at the blade tip, the acceleration of the engine room can comprise the left and right acceleration of the engine room and the front and back acceleration of the engine room, and different engine room acceleration sensors can be arranged on the engine room to obtain the acceleration respectively. The actual value of the detectable variable may be detected as a measure of the detectable variable. The values of the detectable variables may be output by the kinetic model, outputting data for the detectable variable model.
And fusing the model output data of the detectable variable with the measurement data of the detectable variable to obtain fused data of the detectable variable. The model output data and the measurement data are fused, so that more accurate data of the detectable variable can be obtained, and noise influences such as measurement errors and model calculation errors are reduced.
In some optional embodiments, the model output data is fused with the measurement data of the detectable variable using a kalman filter algorithm to obtain fused data. The kalman filter algorithm performs data fusion, which is a conventional data fusion method, and the principle thereof is known and will not be described in detail. In other embodiments, the fusion of the model output data and the measurement data of the detectable variables may also be implemented by using methods such as a bayesian estimation method.
In step S103, a target load of the target portion is determined based on the fusion data. Referring to fig. 6, determining the target load of the target site based on the fused data may further include the steps of:
step S501, determining the current time gain of the dynamic model according to the fusion data and the model output data at the current time. The current time gain can be obtained by comparing the fused data with the model data at the current time, and can be obtained by a formula of the current time gain (fused data/model output data).
Step S502, according to the current data of the section displacement at the current moment and the gain at the current moment, determining the estimated value of the section displacement at the current moment. In some embodiments, the more accurate data of the cross-sectional displacement at the current time can be obtained by a formula of an estimated value of the cross-sectional displacement at the current time (current data of the cross-sectional displacement at the current time × (gain at the current time)).
In step S503, the target load of the target portion is determined based on the estimated value of the cross-sectional displacement at the current time. In some embodiments, the target load may be obtained by calculating the estimated value of the cross-sectional displacement at the current time, so as to achieve the purpose of load prediction of the target portion, where E is the young's modulus, and different materials have different young's moduli.
According to the wind turbine load prediction method of some embodiments of the application, a dynamic model of a target portion of a wind turbine is utilized, model output data of a detectable variable is obtained based on the dynamic model, the model output data and measurement data of the detectable variable are fused to obtain fused data, and then the target load of the target portion is determined. The target load is predicted by using the dynamic model, the dynamic response mechanism of the wind turbine generator is considered, and the prediction result is reliable.
The embodiment of the application further provides a fatigue life estimation method of the wind turbine generator, which comprises the following steps: and determining the fatigue life of the target part by using the target load determined by the wind turbine load prediction method. In some embodiments, the fatigue life of the target part is determined by using the target load, so that the safety condition of the unit can be known in real time conveniently, and the safety of the unit can be maintained.
In some embodiments, the fatigue life of the target portion of the wind turbine is determined based on a fatigue accumulation damage theory by using the target load determined by the wind turbine load prediction method.
In some embodiments, the fatigue life of the target portion is determined by calculating an equivalent fatigue load of the target portion from the predicted target load and then comparing the calculated equivalent fatigue load to design allowable values known at the design stage of the wind turbine. The method for calculating the equivalent fatigue load is an existing calculation method, and is not described.
An embodiment of the present application further provides a load shedding control method, including: and if the target load determined by the wind turbine load prediction method is larger than the load set value of the target part, controlling the wind turbine to carry out load reduction operation. Therefore, the target part of the large load can be identified in time, the load reduction operation is further realized, the unit is protected, and the operation life of the unit is prolonged.
Embodiments of the present application also provide a load prediction system including a memory and a controller. Wherein the memory is for storing a computer program. The processor is used for executing a computer program to realize a wind turbine load prediction method, a fatigue life estimation method or a wind turbine load shedding control method. In some embodiments, the load prediction model is embedded into the main control system of the wind turbine, so that the load control system can be assisted to identify the large-load working condition, the load reduction control is realized, the purpose of protecting the wind turbine is achieved, the fatigue life of the wind turbine can be estimated in time, and the safety of the wind turbine is maintained.
Embodiments of the present application further provide a computer-readable storage medium, configured to store a computer program, where the computer program, when executed by a processor, implements the wind turbine load prediction method, the fatigue life of the wind turbine, or the load shedding control method for the wind turbine described in any of the above embodiments.
The above description is only a preferred embodiment of the present application and should not be taken as limiting the present application, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (11)
1. A wind turbine load prediction method is characterized by comprising the following steps:
obtaining model output data of a detectable variable of a target part by using a dynamic model corresponding to the target part of the wind turbine generator, wherein the dynamic model is constructed according to the detectable variable;
fusing the model output data and the measurement data of the detectable variable to obtain fused data;
and determining the target load of the target part according to the fusion data.
2. The wind turbine load prediction method according to claim 1, characterized in that the input quantities of the dynamical model comprise rotor torque;
the method comprises the following steps:
acquiring a pitch angle and a blade tip speed ratio;
obtaining the wind wheel torque by utilizing a two-dimensional lookup table of wind wheel torque, the pitch angle and the blade tip speed ratio according to the pitch angle and the blade tip speed ratio;
the method for obtaining the model output data of the detectable variable of the target part by using the dynamic model corresponding to the target part of the wind turbine generator set comprises the following steps:
and inputting the wind wheel torque into the dynamic model to obtain the model output data.
3. The wind turbine load prediction method according to claim 1, characterized in that the input quantities of the dynamical model comprise a rotor thrust;
the method comprises the following steps:
acquiring a pitch angle and a blade tip speed ratio;
obtaining the wind wheel thrust by utilizing a two-dimensional lookup table of the wind wheel thrust, the pitch angle and the blade tip speed ratio according to the pitch angle and the blade tip speed ratio;
the method for obtaining the model output data of the detectable variable of the target part by using the dynamic model corresponding to the target part of the wind turbine generator set comprises the following steps:
and inputting the wind wheel thrust into the dynamic model to obtain the model output data.
4. The wind turbine load prediction method according to claim 2 or 3, characterized in that the state quantities of the dynamical model comprise a section displacement and a section velocity of the target portion;
the method for obtaining the model output data of the detectable variable of the target part by using the dynamic model corresponding to the target part of the wind turbine generator set comprises the following steps:
obtaining current data of the section displacement and current data of the section speed at the current moment according to the data of the section displacement and the data of the section speed at the last moment of the dynamic model;
and obtaining the model output data by using the dynamic model comprising the current data of the section displacement and the current data of the section velocity.
5. The wind turbine load prediction method according to claim 4, wherein the determining the target load of the target portion according to the fusion data comprises:
determining the gain of the dynamic model at the current moment according to the fusion data and the model output data at the current moment;
determining an estimated value of the section displacement at the current moment according to the current data of the section displacement at the current moment and the gain at the current moment;
determining a target load of the target portion according to the estimated value of the section displacement at the current moment.
6. The method of wind turbine load prediction according to claim 1, wherein the detectable variables include at least one of generator speed, generator torque, blade pitch angle, blade root bending moment, blade tip acceleration and nacelle acceleration.
7. The wind turbine load prediction method according to claim 1, wherein the fusing the model output data with the measured data of the detectable variable to obtain fused data comprises:
and fusing the model output data and the measurement data of the detectable variable by using a Kalman filtering algorithm to obtain fused data.
8. A fatigue life estimation method for a wind turbine generator is characterized by comprising the following steps:
determining the fatigue life of the target part by using the target load determined by the wind turbine load prediction method according to any one of claims 1 to 7.
9. A load reduction control method of a wind turbine generator is characterized by comprising the following steps:
and if the target load determined by the wind turbine load prediction method according to any one of claims 1 to 7 is greater than the load set value of the target part, controlling the wind turbine to carry out load reduction operation.
10. A wind turbine load prediction system, comprising:
a memory and a processor;
wherein the memory is used for storing a computer program;
the processor is configured to execute the computer program to implement the wind turbine load prediction method according to any one of claims 1 to 7, the fatigue life estimation method for a wind turbine according to claim 8, or the wind turbine load shedding control method according to claim 9.
11. A computer-readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the wind turbine load prediction method of any one of claims 1 to 7, the fatigue life estimation method of a wind turbine of claim 8, or the wind turbine load shedding control method of claim 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210594690.2A CN114909264A (en) | 2022-05-27 | 2022-05-27 | Load prediction method, fatigue life estimation method, load reduction control method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210594690.2A CN114909264A (en) | 2022-05-27 | 2022-05-27 | Load prediction method, fatigue life estimation method, load reduction control method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114909264A true CN114909264A (en) | 2022-08-16 |
Family
ID=82767726
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210594690.2A Pending CN114909264A (en) | 2022-05-27 | 2022-05-27 | Load prediction method, fatigue life estimation method, load reduction control method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114909264A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024088022A1 (en) * | 2022-10-28 | 2024-05-02 | 金风科技股份有限公司 | Wind turbine control method and apparatus, and controller |
-
2022
- 2022-05-27 CN CN202210594690.2A patent/CN114909264A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024088022A1 (en) * | 2022-10-28 | 2024-05-02 | 金风科技股份有限公司 | Wind turbine control method and apparatus, and controller |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11713747B2 (en) | Wind turbine control method | |
CN101821689B (en) | Method and device for providing at least one input sensor signal for control and/or monitoring application and control device | |
EP3221582B1 (en) | A method for estimating a wind speed including calculating a pitch angle adjusted for blade torsion | |
JP4995209B2 (en) | Wind power generator and wind direction estimating method for wind power generator | |
US20130302161A1 (en) | Controller of wind turbine and wind turbine | |
Bergami et al. | A smart rotor configuration with linear quadratic control of adaptive trailing edge flaps for active load alleviation | |
EP3597907A1 (en) | System and method for controlling thrust and/or tower loads of a wind turbine | |
CN110145436A (en) | Non-linear economic model forecast control method applied to blower | |
WO2018047564A1 (en) | State monitoring device for wind power generating device, state monitoring system including same, and state monitoring method for wind power generating device | |
CN107709766A (en) | The method for calibrating the load cell of wind turbine | |
Boorsma et al. | Enhanced approach for simulation of rotor aerodynamic loads | |
CN102418658A (en) | Method of and device for determining a mass condition of a rotor of a wind turbine, and method of operating a wind turbine | |
TWI708893B (en) | Wind power system | |
EP3415752B1 (en) | Variable rated speed control in partial load operation of a wind turbine | |
CN114909264A (en) | Load prediction method, fatigue life estimation method, load reduction control method and system | |
Bottasso et al. | Performance comparison of control schemes for variable-speed wind turbines | |
WO2019150805A1 (en) | Wind power generation device and wind power generation system | |
CN113252938A (en) | Method for determining the wind speed in the rotor plane of a wind turbine | |
EP3259472B1 (en) | Control for a wind turbine | |
EP4166782A1 (en) | Wind turbine model predictive control (mpc) with thrust and/or power correction | |
CN111396251B (en) | Method of operating a wind turbine based on maximum thrust limits | |
Stotsky et al. | Control of wind turbines: A tutorial on proactive perspectives | |
Shi | Model-based detection for ice on wind turbine blades | |
Perez-Becker et al. | Investigations on the Fatigue Load Reduction Potential of Advanced Control Strategies for Multi-MW Wind Turbines using a Free Vortex Wake Model | |
WO2022270025A1 (en) | Method and device for diagnosing remaining service life of wind power generator |
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 |