LU502837B1 - Vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set and the method thereof - Google Patents
Vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set and the method thereof Download PDFInfo
- Publication number
- LU502837B1 LU502837B1 LU502837A LU502837A LU502837B1 LU 502837 B1 LU502837 B1 LU 502837B1 LU 502837 A LU502837 A LU 502837A LU 502837 A LU502837 A LU 502837A LU 502837 B1 LU502837 B1 LU 502837B1
- Authority
- LU
- Luxembourg
- Prior art keywords
- vortex
- vibration
- turbine generator
- induced vibration
- wind turbine
- Prior art date
Links
- 230000001629 suppression Effects 0.000 title claims abstract description 56
- 238000012544 monitoring process Methods 0.000 title claims abstract description 28
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000013528 artificial neural network Methods 0.000 claims abstract description 31
- 230000008569 process Effects 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims description 63
- 238000010200 validation analysis Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 9
- 238000012423 maintenance Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 2
- 238000010248 power generation Methods 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000010801 machine learning Methods 0.000 abstract description 2
- 230000004044 response Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 239000012530 fluid Substances 0.000 description 3
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- RLQJEEJISHYWON-UHFFFAOYSA-N flonicamid Chemical compound FC(F)(F)C1=CC=NC=C1C(=O)NCC#N RLQJEEJISHYWON-UHFFFAOYSA-N 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
- F03D7/02—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor
- F03D7/0296—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor to prevent, counteract or reduce noise emissions
-
- 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
- F03D7/04—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
- 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
- F03D7/0224—Adjusting blade pitch
-
- 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
- F03D7/0232—Adjusting aerodynamic properties of the blades with flaps or slats
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2260/00—Function
- F05B2260/82—Forecasts
- F05B2260/821—Parameter estimation or prediction
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2260/00—Function
- F05B2260/84—Modelling or simulation
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2260/00—Function
- F05B2260/96—Preventing, counteracting or reducing vibration or noise
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2270/00—Control
- F05B2270/30—Control parameters, e.g. input parameters
- F05B2270/32—Wind speeds
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2270/00—Control
- F05B2270/30—Control parameters, e.g. input parameters
- F05B2270/321—Wind directions
-
- 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
- F05B2270/334—Vibration measurements
-
- 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)
- Mechanical Engineering (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Wind Motors (AREA)
Abstract
The present invention discloses a vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set and the method thereof, which relates to the technical field of wind power generation. The steps include: collecting vibration signals of the wind turbine generator system, and wind speed and wind direction signals of wind farms within a period of time at a certain frequency interval; calculating the peak vibration value, effective vibration value, average wind speed and average wind direction of the wind turbine generator system during the collection time period through vibration signals, wind speed and wind direction signals; entering the peak vibration value, effective vibration value, average wind speed and average wind direction into the BP neural network-based prediction model to judge whether vortex-induced vibration occurs in the wind turbine generator system; uploading the alarm information to the cloud server when vortex-induced vibration occurs, and suppressing the vortex-induced vibration through the vortex-induced vibration suppression device. The present invention applies the machine learning algorithm to the vortex-induced vibration response and prediction, which is simple and efficient, avoids the complicated and redundant calculation process, and makes quick and accurate prediction and monitoring of vortex-induced vibration possible.
Description
BL-5559
LU502837
VORTEX-INDUCED VIBRATION SUPPRESSION MONITORING SYSTEM FOR
DOUBLY-FED WIND TURBINE GENERATOR SET AND THE METHOD THEREOF
The present invention relates to the technical field of wind power generation, and more particularly to a vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set and the method thereof.
Wind power generation technology has now become a major contributor to the growing global clean electricity market. Many serious problems may arise during the hoisting process of wind turbine generator. Doubly-fed wind power generator set is of a cylindrical drum tower structure, featuring high tower cylinder and low natural frequency. In this case, vortex-induced vibration may occur, which will lead to great fatigue damage to the set, rapidly deplete the service life of the tower, and may even cause serious damage to the set and the safety of the personnel as a result of going beyond the limit load of the set. According to the prior art, vortex-induced vibration in the energized state is suppressed by yaw to the wind and adjusting the pitch angle of blade, while in the non-energized state, the spoiler is widely used, and the core functional component of the spoiler is the spoiler block or spoiler bar. For instance, the Chinese patent No. CN201821114263.5 relates to a wind turbine tower cylinder spoiler bar that can suppress vortex-induced vibration. However, at present, due to the limitations of the prior art, no efficient solution to forecasting and monitoring vortex-induced vibration is available, making it too late to take corresponding countermeasures when vortex-induced vibration occurs.
In view of the above, the present invention provides a vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set and the method thereof to address the defects as mentioned in the background of the invention.
To achieve the above purpose, the present invention is implemented with the following technical scheme: a vortex-induced vibration suppression monitoring system for doubly-fed 1
BL-5559 wind turbine generator set, comprising a data acquisition module, a data processing module, à 502897 prediction module and a suppression module that are sequentially connected, wherein,
The said data acquisition module is configured to collect vibration signals of the wind turbine generator system, and wind speed and wind direction signals of wind farms within a period of time at a certain frequency interval;
The said data processing module is configured to calculate the peak vibration value, effective vibration value, average wind speed and average wind direction of the wind turbine generator system during the collection time period through the said vibration signals, wind speed and wind direction signals;
The said prediction module is configured to enter the said peak vibration value, effective vibration value, average wind speed and average wind direction into the BP neural network-based prediction model to judge whether vortex-induced vibration occurs in the wind turbine generator system;
The said suppression module is configured to upload the alarm information to the cloud server when vortex-induced vibration occurs, and suppress the vortex-induced vibration through the vortex-induced vibration suppression device.
Optionally, the said data acquisition module comprises a vibration sensor, a wind direction sensor and a wind speed sensor, wherein, the said vibration sensor is arranged inside the cabin or tower cylinder of the wind turbine generator system, and is configured to detect the vibration signal of the wind turbine generator system in real time; the said wind direction sensor and wind speed sensor are arranged on the meteorological rack, and configured to detect the wind speed and wind direction signals in the wind farm area in real time.
Optionally, the said vortex-induced vibration suppression device comprises a first suppression unit and a second suppression unit, which are connected in parallel, wherein the said first suppression unit is a spoiler, and the said second suppression unit is a pitch control device.
Optionally, the said first suppression unit comprises a flexible connector and a spoiler arranged on the flexible connector and a spoiler arranged on the said flexible connector, whose two ends are correspondingly fixed on the upper connecting flange and the lower connecting flange of the anti-vibration tower cylinder section.
Optionally, the said second suppression unit comprises a fan main control cabinet, blades and their drivers, and a variable pitch motor; the blade drivers are respectively connected with a variable pitch motor, and each blade driver is respectively connected with a supercapacitor module that stores energy. 2
BL-5559
Optionally, it further comprises a hub maintenance switch and relay mounted on the engine 502897 room cabinet to control the said pitch control device according to the feedback signal of the said hub maintenance switch.
The present invention also provides a vortex-induced vibration suppression monitoring method for doubly-fed wind turbine generator set, for which a vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set is used for monitoring.
The specific steps are as follows:
Collecting vibration signals of the wind turbine generator system, and wind speed and wind direction signals of wind farms within a period of time at a certain frequency interval; calculating the peak vibration value, effective vibration value, average wind speed and average wind direction of the wind turbine generator system during the collection time period through the said vibration signals, wind speed and wind direction signals; entering the said peak vibration value, effective vibration value, average wind speed and average wind direction into the BP neural network-based prediction model to judge whether vortex-induced vibration occurs in the wind turbine generator system; uploading the alarm information to the cloud server when vortex-induced vibration occurs, and suppressing the vortex-induced vibration through the vortex-induced vibration suppression device.
Optionally, the training process of the said prediction model includes:
Collecting original data required for vortex-induced vibration prediction, and performing standardized processing and classification for the said original data to get a training set, a validation set and a test set;
Initializing the parameters of the neural network and building the neural network, wherein the said parameters contain a training error index value, a validation error index value, a weight and a threshold value;
Training the said neural network with the said training set and validating the said neural network with the said validation set to generate a nonlinear autoregressive neural network featuring a training error less than the training error index value and a validation error less than the validation error index value;
Entering the said test set into the said nonlinear autoregressive neural network to output a final prediction value.
Optionally, when the said training set is input into the said neural network for independent training via each training channel until their respective convergence conditions are met to get a 3
BL-5559 convolutional neural network model covering a plurality of training channels, comprising. 95837 determining parameters of each training channel; entering the training set into the said neural network to get the predicted feature data corresponding to each training channel; determining the prediction error according to the said predicted feature data and the real feature data for each training channel; readjusting the parameters of the corresponding training channel of which the said prediction error is greater than the preset error, repeating the training process of the said corresponding training channel until the prediction error of the said corresponding training channel is less than or equal to the said preset error, and ending the training process of the said corresponding training channel.
According to the above technical scheme and compared with the prior art, the present invention discloses a vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set and the method thereof, and applies the machine learning algorithm in artificial intelligence to the vortex-induced vibration response and prediction, which is simple and efficient, avoids the complicated and redundant calculation process, and makes quick and accurate prediction and timely monitoring of vortex-induced vibration possible. The application of the supercapacitor charger to charge the backup supercapacitor battery of the variable pitch motor for the wind power generator set can ensure that the blade can work for a short time in case of sudden accidents such as power failure, minizing the force exerted on the blade and guaranteeing the safety of the blade. If the external power supply and the motor brake fail at this time, the pitch control system will activate its safety lock protection system. According to the one-way braking principle of the motor brake, the blades will be automatically blown to the feathering position by the wind, which can effectively reduce the absorption of wind energy by the fan after failure.
Brief Introduction of the Drawings
To better describe the embodiment of the present invention or the technical scheme of the prior art, a brief introduction of the accompanying drawings to be used in the descriptions of the embodiment or the prior art is made hereby. Obviously, the drawings below are only the embodiment of the present invention, and for those ordinarily skilled in the art, other drawings based on such drawings can be obtained without making creative endeavors.
Fig. 1 is a system structure diagram of the present invention;
Fig. 2 is a structural diagram of the data acquisition module of the present invention;
Fig. 3 is the vortex-induced vibration diagram of the present invention; 4
BL-5559
Fig. 4 is the flowchart of the method of the present invention. 502837
The technical scheme in the embodiment of the present invention is clearly and completely described below in combination with the drawings thereof. Obviously, the embodiment is just a part of embodiments of the present invention, not all of them. Based on the embodiment of the present invention, all the other embodiments obtained by those ordinarily skilled in the art without making creative endeavors shall fall into the scope of protection of the present invention.
The embodiment of the present invention discloses a vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set, as illustrated in Fig. 1, comprising a data acquisition module, a data processing module, a prediction module and a suppression module that are sequentially connected, wherein,
The data acquisition module is configured to collect vibration signals of the wind turbine generator system, and wind speed and wind direction signals of wind farms within a period of time at a certain frequency interval;
The data processing module is configured to calculate the peak vibration value, effective vibration value, average wind speed and average wind direction of the wind turbine generator system during the collection time period through the said vibration signals, wind speed and wind direction signals.
The prediction module is configured to enter the said peak vibration value, effective vibration value, average wind speed and average wind direction into the BP neural network-based prediction model to judge whether vortex-induced vibration occurs in the wind turbine generator system;
The suppression module is configured to upload the alarm information to the cloud server when vortex-induced vibration occurs, and suppressing the vortex-induced vibration through the vortex-induced vibration suppression device.
As illustrated in Fig. 2, the data acquisition module comprises a vibration sensor, a wind direction sensor and a wind speed sensor, wherein, the vibration sensor is arranged inside the cabin or tower cylinder of the wind turbine generator system, and is configured to detect the vibration signal of the said wind turbine generator system in real time; the wind direction sensor and wind speed sensor are arranged on the meteorological rack, and configured to detect the wind speed and wind direction signals in the wind farm area in real time.
BL-5559
In fluid dynamics, vortex-induced vibration refers to the motion induced by the interaction 502897 between an object and an external fluid on the object itself, or the periodic irregular motion produced on the fluid. When passing through the non-streamlined blunt body, the air flow field will change due to obstruction, and alternating vortices will be periodically generated on both sides behind the blunt body, as illustrated in Fig. 3. This phenomenon is also known as Karman vortex street. In the meantime, the appearance and falling off of vortices will lead to uneven distribution of air pressure in the air flow field, so that the pressure perpendicular to the direction of the air flow field will be periodically generated on both sides of the blunt body. When the blunt body itself has a certain elastic support rather than perfect rigidity, the pressure will force the blunt body to generate a vibration perpendicular to the direction of the air flow field, which is called vortex-induced vibration.
In this embodiment, the vortex-induced vibration suppression device comprises a first suppression unit and a second suppression unit, which are connected in parallel, wherein the first suppression unit is a spoiler, and the second suppression unit is a pitch control device.
Particularly, the first suppression unit comprises a flexible connector and a spoiler arranged on the flexible connector and a spoiler arranged on the flexible connector, whose two ends are correspondingly fixed on the upper connecting flange and the lower connecting flange of the anti-vibration tower cylinder section. The cross-sectional shape of the spoiler is a regular polygon. In other words, the cross-sectional shape of each spoiler block is a regular triangle, a regular quadrangle or a regular pentagon. Since the flexible connector passes through the plurality of spoiler blocks on it through the installation through-hole, the spoiler block can rotate relative to the flexible connector. In order to ensure the vortex-induced vibration prevention effect after the spoiler block is fixed on the tower cylinder, the spoiler block is set as a regular polygon. By doing so, the spoiler block can be fixed on the tower cylinder in a convenient and quick manner.
The second suppression unit comprises a fan main control cabinet, blades and their drivers, and a variable pitch motor; the blade drivers are respectively connected with a variable pitch motor, and each blade driver is respectively connected with a supercapacitor module that stores energy.
The variable pitch motor is a tubular motor, and the motor shaft of each variable pitch motor is also provided with a one-way brake device that automatically returns the blades to the feathering position after loss of power. 6
BL-5559
It further comprises a hub maintenance switch and relay mounted on the engine room 502897 cabinet to control the pitch control device according to the feedback signal of the hub maintenance switch.
Embodiment 2 of the present invention provides a vortex-induced vibration suppression monitoring method for doubly-fed wind turbine generator set, for which a vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set is used for monitoring, as illustrated in Fig. 4. The specific steps are as follows:
S1: Collecting vibration signals of the wind turbine generator system, and wind speed and wind direction signals of wind farms within a period of time at a certain frequency interval,
S2: Calculate the peak vibration value, effective vibration value, average wind speed and average wind direction of the wind turbine generator system during the collection time period through vibration signals, wind speed and wind direction signals;
S3: Entering the peak vibration value, effective vibration value, average wind speed and average wind direction into the BP neural network-based prediction model to judge whether vortex-induced vibration occurs in the wind turbine generator system;
S4: Uploading the alarm information to the cloud server when vortex-induced vibration occurs, and suppressing the vortex-induced vibration through the vortex-induced vibration suppression device.
Further, the training process of the said prediction model includes:
Collecting original data required for vortex-induced vibration prediction, and performing standardized processing and classification for the original data to get a training set, a validation set and a test set;
Initializing the parameters of the neural network and building the neural network, wherein the parameters contain a training error index value, a validation error index value, a weight and a threshold value;
Training the said neural network with the training set and validating the neural network with the validation set to generate a nonlinear autoregressive neural network featuring a training error less than the training error index value and a validation error less than the validation error index value;
Entering the test set into the nonlinear autoregressive neural network to output a final prediction value.
Further, when the training set is input into the neural network for independent training via each training channel until their respective convergence conditions are met to get a convolutional 7
BL-5559 neural network model covering a plurality of training channels, comprising: determining 202837 parameters of each training channel; entering the training set into the said neural network to get the predicted feature data corresponding to each training channel; determining the prediction error according to the predicted feature data and the real feature data for each training channel; readjusting the parameters of the corresponding training channel of which the prediction error is greater than the preset error, repeating the training process of the corresponding training channel until the prediction error of the corresponding training channel is less than or equal to the preset error, and ending the training process of the corresponding training channel.
Each embodiment in this specification is described in a progressive manner, focusing on its differences from other embodiments, and the same and similar parts between embodiments can be referred to mutually. For the device disclosed in the embodiment, the description is relatively simple since it corresponds to the method disclosed in the embodiment, and reference can be made to the method description section when needed.
The above description of the disclosed embodiments enables those skilled in the art to practice or use the present invention. Modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the essence or scope of the present invention. Accordingly, the present invention will not be limited to the embodiments described herein, but will cover the widest scope consistent with the principles and novel features disclosed herein. 8
Claims (9)
1. A vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set, characterized in that it comprises a data acquisition module, a data processing module, a prediction module and a suppression module that are sequentially connected, wherein, The said data acquisition module is configured to collect vibration signals of the wind turbine generator system, and wind speed and wind direction signals of wind farms within a period of time at a certain frequency interval; The said data processing module is configured to calculate the peak vibration value, effective vibration value, average wind speed and average wind direction of the wind turbine generator system during the collection time period through vibration signals, wind speed and wind direction signals; The said prediction module is configured to enter the said peak vibration value, effective vibration value, average wind speed and average wind direction into the BP neural network-based prediction model to judge whether vortex-induced vibration occurs in the wind turbine generator system; The said suppression module is configured to upload the alarm information to the cloud server when vortex-induced vibration occurs, and suppress the vortex-induced vibration through the vortex-induced vibration suppression device.
2. A vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set according to Claim 1, characterized in that the said data acquisition module comprises a vibration sensor, a wind direction sensor and a wind speed sensor; wherein, the said vibration sensor is arranged inside the cabin or tower cylinder of the wind turbine generator system, and is configured to detect the vibration signal of the wind turbine generator system in real time; the said wind direction sensor and wind speed sensor are arranged on the meteorological rack, and configured to detect the wind speed and wind direction signals in the wind farm area in real time.
3. A vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set according to Claim 1, characterized in that the said vortex-induced vibration suppression device comprises a first suppression unit and a second suppression unit, which are connected in parallel, wherein the said first suppression unit is a spoiler, and the said second suppression unit is a pitch control device. 9
BL-5559
4. A vortex-induced vibration suppression monitoring system for doubly-fed wind turbine 502897 generator set according to Claim 3, characterized in that the said first suppression unit comprises a flexible connector and a spoiler arranged on the flexible connector and a spoiler arranged on the said flexible connector, whose two ends are correspondingly fixed on the upper connecting flange and the lower connecting flange of the anti-vibration tower cylinder section.
5. A vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set according to Claim 3, characterized in that the said second suppression unit comprises a fan main control cabinet, blades and their drivers, and a variable pitch motor; the blade drivers are respectively connected with a variable pitch motor, and each blade driver is respectively connected with a supercapacitor module that stores energy.
6. A vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set according to Claim 3, characterized in that it further comprises a hub maintenance switch and relay mounted on the engine room cabinet to control the said pitch control device according to the feedback signal of the said hub maintenance switch.
7. A vortex-induced vibration suppression monitoring method for doubly-fed wind turbine generator set, characterized in that a vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set according to either of Claims 1-6 is used for monitoring. The specific steps are as follows: Collecting vibration signals of the wind turbine generator system, and wind speed and wind direction signals of wind farms within a period of time at a certain frequency interval, Calculating the peak vibration value, effective vibration value, average wind speed and average wind direction of the wind turbine generator system during the collection time period through the said vibration signals, wind speed and wind direction signals; Entering the said peak vibration value, effective vibration value, average wind speed and average wind direction into the BP neural network-based prediction model to judge whether vortex-induced vibration occurs in the wind turbine generator system; Uploading the alarm information to the cloud server when vortex-induced vibration occurs, and suppressing the vortex-induced vibration through the vortex-induced vibration suppression device.
8. A vortex-induced vibration suppression monitoring method for doubly-fed wind turbine generator set according to Claim 7, characterized in that the training process of the said prediction model includes:
BL-5559 Collecting original data required for vortex-induced vibration prediction, and performing 202837 standardized processing and classification for the said original data to get a training set, a validation set and a test set; Initializing the parameters of the neural network and building the neural network, wherein the said parameters contain a training error index value, a validation error index value, a weight and a threshold value; Training the said neural network with the said training set and validating the said neural network with the said validation set to generate a nonlinear autoregressive neural network featuring a training error less than the training error index value and a validation error less than the validation error index value; Entering the said test set into the said nonlinear autoregressive neural network to output a final prediction value.
9. A vortex-induced vibration suppression monitoring method for doubly-fed wind turbine generator set according to Claim 8, characterized in that when the said training set is input into the said neural network for independent training via each training channel until their respective convergence conditions are met to get a convolutional neural network model covering a plurality of training channels, comprising: determining parameters of each training channel; entering the training set into the said neural network to get the predicted feature data corresponding to each training channel; determining the prediction error according to the said predicted feature data and the real feature data for each training channel; readjusting the parameters of the corresponding training channel of which the said prediction error is greater than the preset error, repeating the training process of the said corresponding training channel until the prediction error of the said corresponding training channel is less than or equal to the said preset error, and ending the training process of the said corresponding training channel. 11
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211031664.5A CN115306656A (en) | 2022-08-26 | 2022-08-26 | Vortex-induced vibration suppression monitoring system and method for double-fed wind generating set |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| LU502837B1 true LU502837B1 (en) | 2024-02-26 |
Family
ID=83546827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| LU502837A LU502837B1 (en) | 2022-08-26 | 2022-09-26 | Vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set and the method thereof |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115306656A (en) |
| LU (1) | LU502837B1 (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100283245A1 (en) * | 2009-05-07 | 2010-11-11 | Vestas Wind Systems A/S | Wind turbine |
| CN112664411A (en) * | 2021-01-22 | 2021-04-16 | 长沙理工大学 | Method for controlling resonance of wind turbine generator by monitoring wind speed |
| CN113642068A (en) * | 2021-07-07 | 2021-11-12 | 哈尔滨工业大学 | Bridge vortex-induced vibration amplitude prediction method based on decision tree and recurrent neural network |
| US11261844B2 (en) * | 2019-02-28 | 2022-03-01 | General Electric Company | System and method for predicting wind turbine shutdowns due to excessive vibration |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104329223B (en) * | 2014-11-11 | 2017-05-03 | 沈阳华创风能有限公司 | Variable-pitch system of wind generating set |
| CN104405582A (en) * | 2014-11-13 | 2015-03-11 | 湖南世优电气股份有限公司 | Wheel hub safety chain of megawatt wind generating set and control method thereof |
| CN105927479B (en) * | 2016-06-20 | 2019-05-07 | 新疆金风科技股份有限公司 | The installation method of wind power generating set |
| CN108090629B (en) * | 2018-01-16 | 2021-02-09 | 广州大学 | Load prediction method and system based on nonlinear autoregressive neural network |
| CN110276345B (en) * | 2019-06-05 | 2021-09-17 | 北京字节跳动网络技术有限公司 | Convolutional neural network model training method and device and computer readable storage medium |
| CN111878324A (en) * | 2020-08-28 | 2020-11-03 | 国电联合动力技术有限公司 | Wind power plant tower drum vortex-induced vibration early warning method and early warning system |
| CN112360684B (en) * | 2020-10-27 | 2022-07-12 | 中车株洲电力机车研究所有限公司 | Method for inhibiting vortex-induced vibration of fan |
| CN215633528U (en) * | 2021-06-29 | 2022-01-25 | 华能新能源股份有限公司 | Monitoring and inhibiting system for vortex-induced vibration of wind turbine generator flexible tower |
| CN114776522B (en) * | 2022-06-22 | 2022-09-02 | 华能酒泉风电有限责任公司 | Method for solving vortex-induced vibration of wind turbine generator |
-
2022
- 2022-08-26 CN CN202211031664.5A patent/CN115306656A/en active Pending
- 2022-09-26 LU LU502837A patent/LU502837B1/en active IP Right Grant
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100283245A1 (en) * | 2009-05-07 | 2010-11-11 | Vestas Wind Systems A/S | Wind turbine |
| US11261844B2 (en) * | 2019-02-28 | 2022-03-01 | General Electric Company | System and method for predicting wind turbine shutdowns due to excessive vibration |
| CN112664411A (en) * | 2021-01-22 | 2021-04-16 | 长沙理工大学 | Method for controlling resonance of wind turbine generator by monitoring wind speed |
| CN113642068A (en) * | 2021-07-07 | 2021-11-12 | 哈尔滨工业大学 | Bridge vortex-induced vibration amplitude prediction method based on decision tree and recurrent neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115306656A (en) | 2022-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3749853B1 (en) | Determining control settings for a wind turbine | |
| CN104019000B (en) | The loading spectrum of wind power generating set is determined and perspective maintenance system | |
| CN101737245B (en) | Blade pitch management method and system | |
| CA2630288C (en) | Method of operating a wind turbine and wind turbine | |
| US11306699B2 (en) | Method for load reduction on wind turbine blade pitch bearings | |
| CN103080540A (en) | Control of wind turbines in a wind park | |
| CN112253406B (en) | Environment load prediction method and vibration pre-control system for offshore wind turbine generator | |
| CN103216383B (en) | Control system and control method for wind generating set | |
| US9926912B2 (en) | System and method for estimating wind coherence and controlling wind turbine based on same | |
| CN112459965A (en) | Yaw optimization control method, device, equipment and medium considering wind power plant wake flow | |
| CN112031996B (en) | Method and system for optimizing over-limit of cabin vibration during yaw motion of wind turbine generator | |
| EP3263890A1 (en) | Methods and systems for feedforward control of wind turbines | |
| US20220307476A1 (en) | Wind turbine, wind power plant and method for controlling a wind turbine and a wind power plant | |
| CN106351792A (en) | Load reducing system of wind generator set and working method of load reducing system | |
| CN111502915A (en) | Wind turbine generator intelligent control system and method based on laser radar wind measurement | |
| CN105134490A (en) | Method for improving economy of wind turbine generator set | |
| LU502837B1 (en) | Vortex-induced vibration suppression monitoring system for doubly-fed wind turbine generator set and the method thereof | |
| CN201671762U (en) | Hydraulic drive independent pitching redundant control system with low voltage ride-through function | |
| CN206319995U (en) | A kind of load reduction system of Wind turbines | |
| CN111075649A (en) | Active load reduction control method of wind generating set based on external wind conditions | |
| JP2014202190A (en) | Control apparatus, control method, and program | |
| US10190574B2 (en) | System and method for controlling generation output quantity of a wind power plant using dust detector | |
| CN105649896A (en) | Intelligent monitoring operation control system for wind turbine unit and control method thereof | |
| CN112922778B (en) | Yaw optimization method, system, equipment and storage medium for wind turbine generator | |
| EP4115079B1 (en) | Control method and device of a wind park |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FG | Patent granted |
Effective date: 20240226 |