CN117607493A - Anemograph calibration method and system in vibration environment - Google Patents
Anemograph calibration method and system in vibration environment Download PDFInfo
- Publication number
- CN117607493A CN117607493A CN202311135656.XA CN202311135656A CN117607493A CN 117607493 A CN117607493 A CN 117607493A CN 202311135656 A CN202311135656 A CN 202311135656A CN 117607493 A CN117607493 A CN 117607493A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- anemometer
- wind
- sensor
- vibration
- 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 36
- 238000010801 machine learning Methods 0.000 claims abstract description 7
- 238000000611 regression analysis Methods 0.000 claims abstract description 7
- 238000005259 measurement Methods 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000005096 rolling process Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 210000002569 neuron Anatomy 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010248 power generation Methods 0.000 abstract description 7
- 238000012423 maintenance Methods 0.000 abstract description 6
- 238000012544 monitoring process Methods 0.000 description 5
- 108010066057 cabin-1 Proteins 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000004164 analytical calibration Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P21/00—Testing or calibrating of apparatus or devices covered by the preceding groups
- G01P21/02—Testing or calibrating of apparatus or devices covered by the preceding groups of speedometers
- G01P21/025—Testing or calibrating of apparatus or devices covered by the preceding groups of speedometers for measuring speed of fluids; for measuring speed of bodies relative to fluids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P21/00—Testing or calibrating of apparatus or devices covered by the preceding groups
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Indicating Or Recording The Presence, Absence, Or Direction Of Movement (AREA)
Abstract
The invention discloses a method and a system for calibrating an anemoclinograph in a vibration environment, and belongs to the technical field of wind power generation. A newly installed anemometer sensor is arranged in the area where the original anemometer sensor is located, a wind speed and direction value reference value is collected, and wind speed and direction measured values collected by the original anemometer sensor are preprocessed; setting a horizontal vibration sensor and a vertical vibration sensor in the horizontal direction and the vertical direction of the area where the original anemometer sensor is located, and respectively acquiring vibration data in the horizontal direction and the vertical direction; and respectively adopting a regression analysis method and a machine learning method, establishing a calibration relation model from the wind speed and direction measured value to the wind speed and direction reference value under different vibration frequencies and amplitudes, and carrying out real-time online calibration on the wind speed and direction measured value acquired by the original anemometer sensor. The method can ensure the accuracy of wind speed and wind direction data of the wind turbine generator, optimize the power generation efficiency and stability and improve the safety of wind power operation and maintenance.
Description
Technical Field
The invention belongs to the technical field of wind power generation, and particularly relates to a calibration method and a calibration system for an anemoclinograph in a vibration environment.
Background
The wind speed and the wind direction measured by the anemometer are one of key parameters of the generating efficiency and the stability of the wind turbine generator. Along with the continuous development of the wind turbine generator system towards the directions of longer blade size and larger single machine power, the accuracy requirement on wind speed and direction data is higher and higher. These data are used to adjust the blade angle and impeller wind direction to orient the fan in the most favorable wind direction to maximize the utilization of wind energy and increase the power generation efficiency.
However, the anemoclinograph operates under severe environmental factors for a long time, such as serious abrasion of parts, loose connection, low-temperature icing and the like caused by accumulation of dust and oil drops and long-term rotation, and measurement errors are possibly increased, so that the misalignment and even failure of measurement results are caused, and the generating efficiency of the unit is seriously affected. Among other things, vibration factors are a relatively common cause of misalignment failure of anemometers.
In early-stage operation fans, the anemoclinographs mainly adopt mechanical and ultrasonic modes, and the measurement results are gradually misaligned along with the increase of the number of operation years. Although the accuracy of the measurement result can be remarkably improved by replacing a new anemometer, the cost is higher; the traditional static calibration method requires complex instruments and equipment, increases the cost and complexity of the calibration process, lacks automation and real-time performance, leads to lower calibration efficiency and is not suitable for the requirement of large-scale instrument calibration.
Disclosure of Invention
In order to solve the defects in the prior art, the invention aims to provide a calibration method and a calibration system for an anemometer under a vibration environment, which introduce vibration monitoring and automatic calibration to realize high-precision and high-efficiency calibration for the anemometer under a real vibration environment and improve the reliability of the calibration; the accuracy of wind speed and wind direction data of the wind turbine generator is ensured, the generating efficiency and stability of a wind power plant are optimized, and the safety of wind power operation and maintenance is improved.
The invention is realized by the following technical scheme:
the invention discloses a calibration method of an anemoclinograph in a vibration environment, which comprises the following steps:
s1: a newly-installed anemometer sensor is arranged in the area where the original anemometer sensor is located, and the anemometer measured value acquired by the original anemometer sensor is preprocessed by utilizing the anemometer value reference value acquired by the newly-installed anemometer sensor;
s2: setting a horizontal direction vibration sensor in the horizontal direction of the area where the original anemometer sensor is located, setting a vertical direction vibration sensor in the vertical direction, and respectively acquiring vibration data in the horizontal direction and the vertical direction;
s3: establishing a calibration relation model from the wind speed and direction measured value to the wind speed and direction reference value under different vibration frequencies and amplitudes by using the preprocessed wind speed and direction measured value obtained in the step S1 and the vibration data in the horizontal direction and the vertical direction obtained in the step S2 respectively through a regression analysis method and a machine learning method;
s4: and (3) carrying out real-time online calibration on wind speed and wind direction measured values acquired by the original wind speed and wind direction indicator sensor by using the calibration relation model obtained in the step (S3).
Preferably, in S1, the newly installed anemometer sensor is the same model as the original anemometer sensor.
Preferably, in S1, the preprocessing includes data cleaning and outlier removal on the collected wind speed and direction values.
Preferably, in S2, the vibration data in the horizontal direction includes a roll amplitude and a roll frequency; vibration data in the vertical direction pitch amplitude and pitch frequency.
Further preferably, in S3, the calibration relation between the wind speed and direction measurement value and the wind speed and direction reference value at different vibration frequencies and amplitudes is expressed as:
wherein f is the vibration frequency (Hz), A is the amplitude (m/s 2 ) V is wind speed (m/s), θ is wind direction (°), V C For the calibrated wind speed value (m/s), θ C Is the calibrated wind direction value (°);
f (V, f, A) is a calibration function of wind speed, g (θ, f, A) is a calibration function of wind direction; the vibration frequency f is the average of the roll frequency and the pitch frequency, and the amplitude a is the average of the roll amplitude and the pitch amplitude.
Further preferably, if the polynomial fitting relation is satisfied before and after the wind speed and direction calibration, the wind speed and direction calibration relation is expressed as:
wherein k is 1 、k 2 、k 3 、k 4 And as a calibration coefficient, the wind speed and direction measurement value is determined by fitting analysis with a wind speed and direction reference value.
Further preferably, the calibration relation model for establishing the wind speed and direction measured value to the wind speed and direction reference value under different vibration frequencies and amplitudes is specifically: establishing a mapping relation model between input data and target output based on a BP neural network, wherein the input data is a wind speed and wind direction measured value, a pitching amplitude, a pitching frequency, a rolling amplitude and a rolling frequency, and the target output is a wind speed and wind direction reference value; dividing the wind speed and direction measured value obtained in the step S1, the wind speed and direction measured value reference value, the pitching amplitude, the pitching frequency, the rolling amplitude and the rolling frequency obtained in the step S2 into a training set and a test set, establishing a wind speed and direction calibration relation model by using the training set, and checking the prediction precision of the established wind speed and direction calibration relation model by using the test set.
Further preferably, the data in the training set is 80% and the data in the test set is 20%.
Further preferably, after the calibration relation model is established, parameters of the calibration relation model are optimized, specifically: the wind speed and wind direction calibration relation model established by adjusting the number of hidden layer nodes and the number of neurons of the adjustable parameter of the BP neural network is continuously trained and tested, the prediction precision of the model is gradually improved, wherein the main adjustable parameter of the BP neural network comprises the number of hidden layer nodes and the number of neurons, the number of neurons can be sequentially selected from 10, 15 and 20 … … by adopting a cyclic traversal method, and the number of hidden layer nodes meets the following formula:
wherein h represents the number of hidden layer nodes, m represents the number of input layer nodes, n represents the number of output layer nodes, and a is an adjustment constant between 1 and 10.
The invention discloses an anemometer calibration system in a vibration environment, which comprises a newly-installed anemometer sensor, a horizontal vibration sensor, a vertical vibration sensor, a anemometer and wind direction measurement value preprocessing module, a calibration relation model building module and an online calibration module, wherein the newly-installed anemometer sensor is connected with the horizontally-installed anemometer sensor; the newly-installed anemometer sensor is arranged in the area where the original anemometer sensor is positioned at the top of the wind turbine nacelle, the horizontal direction vibration sensor is arranged in the horizontal direction of the area where the original anemometer sensor is positioned, and the vertical direction vibration sensor is arranged in the vertical direction of the area where the original anemometer sensor is positioned;
the wind speed and direction measured value preprocessing module is used for preprocessing wind speed and direction measured values acquired by the original anemometer sensor by utilizing a wind speed and direction value reference value acquired by the newly installed anemometer sensor;
the calibration relation model building module is used for building a calibration relation model from the wind speed and wind direction measured value to the wind speed and wind direction reference value under different vibration frequencies and amplitudes by using the preprocessed wind speed and wind direction measured value, the vibration data in the horizontal direction and the vibration data in the vertical direction, which are collected by the horizontal direction vibration sensor and the vertical direction vibration sensor, and a regression analysis method and a machine learning method;
and the online calibration module is used for carrying out real-time online calibration on wind speed and wind direction measured values acquired by the original wind speed and wind direction indicator sensor by using the calibration relation model.
Compared with the prior art, the invention has the following beneficial technical effects:
according to the method for calibrating the anemoclinograph in the vibration environment, vibration monitoring and automatic calibration are introduced, so that the anemoclinograph can be calibrated with high precision and high efficiency in the real vibration environment. By accurately measuring the vibration frequency, amplitude and direction of the anemometer, the influence degree of vibration factors on the measurement result of the anemometer is quantized, and therefore the reliability of calibration is improved. The method is simple and easy to implement, wind speed and direction calibration is carried out by collecting the measurement data and vibration data of the anemometer, unnecessary tower climbing maintenance is avoided, and the operation and maintenance cost of the wind farm is reduced. Meanwhile, the method has the advantages of real-time monitoring and adjustment, and the real-time monitoring and adjustment of the wind turbine generator are realized by connecting the method to the wind power control system in real time, so that the power generation efficiency and the operation and maintenance safety are improved. The method can also realize high-precision calibration, realizes high-precision calibration of the anemoclinograph through optimization and automatic calibration flow of a calibration algorithm, and improves measurement accuracy and stability.
The anemograph calibration system under the vibration environment disclosed by the invention is simple in construction, can be well compatible with the existing fan control monitoring system, and has a good application prospect.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention;
FIG. 2 is a schematic diagram of an anemometer sensor and vibration sensor arrangement of the present invention;
FIG. 3 is a diagram of the system of the present invention.
In the figure: the wind power generation system comprises a wind power cabin 1, an original anemometer sensor 2, a newly-installed anemometer sensor 3, a horizontal vibration sensor 4 and a vertical vibration sensor 5.
Detailed Description
The invention will now be described in further detail with reference to the drawings and to specific embodiments, which are intended to be illustrative rather than limiting.
As shown in FIG. 1, the calibration method of the anemometer under the vibration environment comprises the following steps:
s1: a newly-installed anemometer sensor 3 is arranged in the area where the original anemometer sensor 2 is located, and the anemometer measured value acquired by the original anemometer sensor 2 is preprocessed by utilizing the anemometer value reference value acquired by the newly-installed anemometer sensor 3.
The newly-installed anemometer sensor 3 is newly shipped and has the same model as the original anemometer sensor 2. The preprocessing comprises data cleaning and abnormal value removal of the collected wind speed and direction values so as to obtain more accurate and stable actual wind speed and direction data.
The newly-installed anemometer sensor 3 only retains the newly-installed anemometer during the test of the collected data, and the newly-installed anemometer is detached after the test is finished and used for calibrating the wind speed and the wind direction of the next wind turbine generator system.
S2: a horizontal direction vibration sensor 4 is arranged in the horizontal direction of the area where the original anemometer sensor 2 is arranged, a vertical direction vibration sensor 5 is arranged in the vertical direction, and vibration data in the horizontal direction and the vertical direction are respectively acquired.
The vibration data in the horizontal direction includes a roll amplitude and a roll frequency; vibration data in the vertical direction pitch amplitude and pitch frequency.
S3: and (3) establishing a calibration relation model from the wind speed and direction measured value to the wind speed and direction reference value under different vibration frequencies and amplitudes by using the preprocessed wind speed and direction measured value obtained in the step (S1) and the vibration data in the horizontal direction and the vertical direction obtained in the step (S2) and respectively adopting a regression analysis method and a machine learning method.
The calibration relationship of the anemometer to the anemometer reference value at different vibration frequencies and amplitudes is expressed as:
wherein f is the vibration frequency (Hz), A is the amplitude (m/s 2 ) V is wind speed (m/s), θ is wind direction (°), V C For the calibrated wind speed value (m/s), θ C Is the calibrated wind direction value (°);
f (V, f, A) is a calibration function of wind speed, g (θ, f, A) is a calibration function of wind direction; the vibration frequency f is the average of the roll frequency and the pitch frequency, and the amplitude a is the average of the roll amplitude and the pitch amplitude.
If the polynomial fitting relation is satisfied before and after the wind speed and direction calibration, the wind speed and direction calibration relation is expressed as:
wherein k is 1 、k 2 、k 3 、k 4 For the calibration coefficient, the wind speed and direction measurement value and the wind speed and direction base are used forAnd (5) determining a quasi-value fitting analysis.
The calibration relation model for establishing the wind speed and direction measured value to the wind speed and direction reference value under different vibration frequencies and amplitudes is specifically as follows: establishing a mapping relation model between input data and target output based on a BP neural network, wherein the input data is a wind speed and wind direction measured value, a pitching amplitude, a pitching frequency, a rolling amplitude and a rolling frequency, and the target output is a wind speed and wind direction reference value; dividing the wind speed and direction measured value obtained in the step S1, the wind speed and direction measured value reference value, the pitching amplitude, the pitching frequency, the rolling amplitude and the rolling frequency obtained in the step S2 into a training set and a test set, establishing a wind speed and direction calibration relation model by using the training set, and checking the prediction precision of the established wind speed and direction calibration relation model by using the test set.
The data in the training set was 80% and the data in the test set was 20%.
After the calibration relation model is established, parameters of the calibration relation model are optimized, specifically: the wind speed and wind direction calibration relation model established by adjusting the number of hidden layer nodes and the number of neurons of the adjustable parameter of the BP neural network is continuously trained and tested, the prediction precision of the model is gradually improved, wherein the main adjustable parameter of the BP neural network comprises the number of hidden layer nodes and the number of neurons, the number of neurons can be sequentially selected from 10, 15 and 20 … … by adopting a cyclic traversal method, and the number of hidden layer nodes meets the following formula:
wherein h represents the number of hidden layer nodes, m represents the number of input layer nodes, n represents the number of output layer nodes, and a is an adjustment constant between 1 and 10.
S4: and (3) carrying out real-time online calibration on the wind speed and wind direction measured value acquired by the original wind speed and wind direction indicator sensor 2 by using the calibration relation model obtained in the step (S3).
In practical application, the method is integrated into a wind power control system to realize real-time online calibration of wind speed and wind direction, and the result after wind speed and wind direction calibration can be displayed on a man-machine interaction terminal interface to guide the wind turbine generator to perform operations such as pitch control, yaw control, safety chain control and the like according to the corrected wind speed and wind direction reference value, so that the power generation efficiency and operation and maintenance safety of the wind turbine generator are effectively improved.
As shown in fig. 2 and 3, the anemometer calibration system in the vibration environment of the invention comprises a newly-installed anemometer sensor 3, a horizontal vibration sensor 4, a vertical vibration sensor 5, a wind speed and direction measurement value preprocessing module, a calibration relation model establishing module and an online calibration module; the newly-installed anemometer sensor 3 is arranged in the area where the original anemometer sensor 2 is positioned at the top of the wind power cabin 1, the horizontal direction vibration sensor 4 is arranged in the horizontal direction of the area where the original anemometer sensor 2 is positioned, and the vertical direction vibration sensor 5 is arranged in the vertical direction of the area where the original anemometer sensor 2 is positioned;
the wind speed and direction measurement value preprocessing module is used for preprocessing wind speed and direction measurement values acquired by the original anemometer sensor 2 by utilizing a wind speed and direction value reference value acquired by the newly installed anemometer sensor 3;
the calibration relation model building module is used for building a calibration relation model from the wind speed and wind direction measured value to the wind speed and wind direction reference value under different vibration frequencies and amplitudes by using the preprocessed wind speed and wind direction measured value and vibration data in the horizontal direction and the vertical direction collected by the horizontal direction vibration sensor 4 and the vertical direction vibration sensor 5 respectively through a regression analysis method and a machine learning method;
and the online calibration module is used for carrying out real-time online calibration on the wind speed and wind direction measured value acquired by the original wind speed and wind direction indicator sensor 2 by using a calibration relation model.
It is to be understood that the foregoing description is only a part of the embodiments of the present invention, and that the equivalent changes of the system described according to the present invention are included in the protection scope of the present invention. Those skilled in the art can substitute the described specific examples in a similar way without departing from the structure of the invention or exceeding the scope of the invention as defined by the claims, all falling within the scope of protection of the invention.
Claims (10)
1. A method for calibrating an anemometer in a vibratory environment, comprising:
s1: a newly-installed anemometer sensor (3) is arranged in the area where the original anemometer sensor (2) is located, and wind speed and wind direction measured values acquired by the original anemometer sensor (2) are preprocessed by utilizing wind speed and wind direction value reference values acquired by the newly-installed anemometer sensor (3);
s2: a horizontal direction vibration sensor (4) is arranged in the horizontal direction of the area where the original anemometer sensor (2) is arranged, a vertical direction vibration sensor (5) is arranged in the vertical direction, and vibration data in the horizontal direction and the vertical direction are respectively acquired;
s3: establishing a calibration relation model from the wind speed and direction measured value to the wind speed and direction reference value under different vibration frequencies and amplitudes by using the preprocessed wind speed and direction measured value obtained in the step S1 and the vibration data in the horizontal direction and the vertical direction obtained in the step S2 respectively through a regression analysis method and a machine learning method;
s4: and (3) carrying out real-time online calibration on wind speed and wind direction measured values acquired by the original wind speed and wind direction indicator sensor (2) by using the calibration relation model obtained in the step (S3).
2. The method for calibrating an anemometer under a vibration environment according to claim 1, wherein in S1, the newly installed anemometer sensor (3) is the same type as the original anemometer sensor (2).
3. The method for calibrating an anemometer under a vibration environment according to claim 1, wherein in S1, the preprocessing includes data cleaning and outlier removal of the collected anemometer direction values.
4. The method for calibrating an anemometer under a vibration environment according to claim 1, wherein in S2, the vibration data in the horizontal direction includes a roll amplitude and a roll frequency; vibration data in the vertical direction pitch amplitude and pitch frequency.
5. The method for calibrating an anemometer under a vibration environment according to claim 4, wherein in S3, a calibration relation between a anemometer and a anemometer reference value under different vibration frequencies and amplitudes is expressed as:
wherein f is the vibration frequency, A is the amplitude, V is the wind speed, θ is the wind direction, V C For calibrated wind speed value, θ C The wind direction value after the calibration;
f (V, f, A) is a calibration function of wind speed, g (θ, f, A) is a calibration function of wind direction; the vibration frequency f is the average of the roll frequency and the pitch frequency, and the amplitude a is the average of the roll amplitude and the pitch amplitude.
6. The method for calibrating an anemometer under a vibration environment according to claim 5, wherein if the polynomial fitting relation is satisfied before and after the calibration of the wind speed and direction, the wind speed and direction calibration relation is expressed as:
wherein k is 1 、k 2 、k 3 、k 4 And as a calibration coefficient, the wind speed and direction measurement value is determined by fitting analysis with a wind speed and direction reference value.
7. The method for calibrating an anemometer under a vibration environment according to claim 6, wherein the calibration relation model for establishing the anemometer from the anemometer to the anemometer reference value under different vibration frequencies and amplitudes is specifically: establishing a mapping relation model between input data and target output based on a BP neural network, wherein the input data is a wind speed and wind direction measured value, a pitching amplitude, a pitching frequency, a rolling amplitude and a rolling frequency, and the target output is a wind speed and wind direction reference value; dividing the wind speed and direction measured value obtained in the step S1, the wind speed and direction measured value reference value, the pitching amplitude, the pitching frequency, the rolling amplitude and the rolling frequency obtained in the step S2 into a training set and a test set, establishing a wind speed and direction calibration relation model by using the training set, and checking the prediction precision of the established wind speed and direction calibration relation model by using the test set.
8. The method of calibrating an anemometer under a vibratory environment of claim 7 wherein the data in the training set is 80% and the data in the test set is 20%.
9. The method for calibrating an anemometer under a vibration environment according to claim 7, wherein after the calibration relation model is established, parameters of the calibration relation model are optimized, specifically: the wind speed and wind direction calibration relation model established by adjusting the number of hidden layer nodes and the number of neurons of the adjustable parameter of the BP neural network is continuously trained and tested, the prediction precision of the model is gradually improved, wherein the main adjustable parameter of the BP neural network comprises the number of hidden layer nodes and the number of neurons, the number of neurons can be sequentially selected from 10, 15 and 20 … … by adopting a cyclic traversal method, and the number of hidden layer nodes meets the following formula:
wherein h represents the number of hidden layer nodes, m represents the number of input layer nodes, n represents the number of output layer nodes, and a is an adjustment constant between 1 and 10.
10. The anemometer calibration system in the vibration environment is characterized by comprising a newly-installed anemometer sensor (3), a horizontal vibration sensor (4), a vertical vibration sensor (5), a wind speed and direction measurement value preprocessing module, a calibration relation model building module and an online calibration module; the newly-installed anemometer sensor (3) is arranged in the area where the original anemometer sensor (2) at the top of the wind power cabin (1) is positioned, the horizontal direction vibration sensor (4) is arranged in the horizontal direction of the area where the original anemometer sensor (2) is positioned, and the vertical direction vibration sensor (5) is arranged in the vertical direction of the area where the original anemometer sensor (2) is positioned;
the wind speed and wind direction measurement value preprocessing module is used for preprocessing wind speed and wind direction measurement values acquired by the original wind speed and wind direction sensor (2) by utilizing a wind speed and wind direction value reference value acquired by the newly installed wind speed and wind direction sensor (3);
the calibration relation model building module is used for building a calibration relation model from the wind speed and wind direction measured value to the wind speed and wind direction reference value under different vibration frequencies and amplitudes by using the preprocessed wind speed and wind direction measured value and vibration data in the horizontal direction and the vertical direction, which are collected by the horizontal direction vibration sensor (4) and the vertical direction vibration sensor (5), and respectively adopting a regression analysis method and a machine learning method;
and the online calibration module is used for carrying out real-time online calibration on wind speed and wind direction measured values acquired by the original wind speed and wind direction indicator sensor (2) by using a calibration relation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311135656.XA CN117607493A (en) | 2023-09-04 | 2023-09-04 | Anemograph calibration method and system in vibration environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311135656.XA CN117607493A (en) | 2023-09-04 | 2023-09-04 | Anemograph calibration method and system in vibration environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117607493A true CN117607493A (en) | 2024-02-27 |
Family
ID=89943056
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311135656.XA Pending CN117607493A (en) | 2023-09-04 | 2023-09-04 | Anemograph calibration method and system in vibration environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117607493A (en) |
-
2023
- 2023-09-04 CN CN202311135656.XA patent/CN117607493A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1793123B1 (en) | Correction method for wind speed measurement at wind turbine nacelle | |
| KR101706508B1 (en) | Data Analysis System of Mechanical Load Measurement Data for Wind Turbine | |
| US9004862B2 (en) | Calibration of wind turbine sensor | |
| CN106815773A (en) | A kind of wind power method of evaluating characteristic | |
| CN115544883A (en) | Online measurement method and system for load and platform deformation of floating type offshore wind turbine generator | |
| CN108869174A (en) | A kind of blade of wind-driven generator intrinsic frequency operating condition compensation method of Nonlinear Modeling | |
| CN113033009B (en) | Real-time calculation method for wake flow loss of offshore wind farm in service | |
| CN102797631A (en) | Method, system and device for carrying out online self-correcting on optimal gain of wind generating set | |
| CN115218801A (en) | Machine vision-based wind driven generator clearance distance measuring method and device | |
| CN105041584B (en) | A kind of Wind turbines tower body slope meter calculates method | |
| CN116484652B (en) | Wake flow interference detection method in wind power plant based on blade root load | |
| US11274656B2 (en) | Method of determining a power curve of a wind turbine | |
| CN117590027A (en) | Deficiency correction method and system for wind meter of wind turbine generator and electronic equipment | |
| CN117607493A (en) | Anemograph calibration method and system in vibration environment | |
| CN114458516B (en) | On-line indirect measurement system and method for pitching and yawing moments of wind energy or tidal current energy generator set | |
| CN113807693B (en) | Wind turbine generator generating capacity optimization effect evaluation method based on airborne radar | |
| CN114439703A (en) | Wind turbine generator blade imbalance fault monitoring method based on vehicle-mounted device | |
| CN113565697A (en) | Impeller pneumatic unbalance optimization system and method based on laser and video measurement | |
| CN114186407A (en) | Wind power plant wake velocity field calculation method and system with parameters capable of being adjusted in self-adaptive mode | |
| CN114398842A (en) | Method for evaluating generated energy of operating wind power plant | |
| CN112861301A (en) | Wind power plant theoretical power intelligent calculation method based on real-time data of fans | |
| CN214836884U (en) | Device for measuring power characteristics of offshore wind turbine generator system | |
| CN219319442U (en) | Gyroscope speed measuring sensor calibration system of wind power variable pitch driver | |
| CN111476679A (en) | Method for correcting power curve of wind turbine generator according to atmospheric stability | |
| Hegedus et al. | Research grade data logging monitoring system for wind energy farms |
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 |