Method and system for verifying performance of wind speed and wind direction sensor of wind turbine generator

Abstract

The invention provides a wind turbine generator wind speed and direction sensor performance verification method and system, and the method comprises the steps: selecting a reference unit for verifying the performance of a test unit based on constraint conditions; collecting verification data according to a wind speed segmentation requirement within a set time length; the verification data is the potential generating capacity of the wind turbine generator; calculating a dynamic reference for performance verification based on the spatial correlation weight of the reference unit and the test unit; and performing multi-dimensional evaluation on the replaced wind speed and direction sensor based on the dynamic reference. According to the method, the spatial correlation between the wind speed and the wind direction between the adjacent units in the wind power plant is utilized, the potential generating capacity of the adjacent units is selected as the comparison standard, and the comparison standard has enough stability due to the fact that the wind field environment is not changed, so that stable performance evaluation is achieved for operation of the replaced wind speed and wind direction sensor; the technical problem that the replacement effect of the wind speed and direction sensor is difficult to quantitatively evaluate is solved.

Description

Technical Field

[0001] This invention relates to the field of wind power generation technology, and more specifically, to a method and system for verifying the performance of a wind turbine generator after the wind speed and direction sensors have been replaced. Background Technology

[0002] Currently, in the field of wind power generation technology, wind speed and direction sensors are key sensing components of wind turbine units, and their measurement accuracy directly affects the control performance and power generation efficiency of the unit. Especially in large wind farms, because sensors are exposed to harsh natural environments for a long time, they are prone to performance degradation or sudden failures, requiring regular replacement or maintenance.

[0003] However, there are the following technical bottlenecks in comparing and verifying the performance of the replaced wind speed and direction sensors:

[0004] First, environmental interference leads to poor data comparability. Natural wind itself has strong fluctuations and randomness in time and space, making it difficult to directly use for performance comparison before and after sensor replacement.

[0005] Second, the verification benchmark is lacking. Currently, the commonly used method uses historical data from a single unit as the evaluation benchmark, that is, using the unit's data before the wind speed and direction sensors were replaced as a benchmark to evaluate the unit's data after the sensor replacement. This method cannot exclude dynamic changes in wind resources at the farm level and is difficult to accurately reflect the impact of the sensor's own performance after replacement.

[0006] Third, the quantitative evaluation standards have shortcomings. Existing evaluation systems mostly rely on simple statistical indicators, such as mean, variance, or correlation analysis, resulting in evaluation results that lack spatial consistency and robustness. Summary of the Invention

[0007] To overcome the shortcomings of the prior art, this invention proposes a method and system for verifying the performance of wind speed and direction sensors for wind turbines. Utilizing the spatial correlation between wind speed and direction between adjacent turbines in a wind farm, the potential power generation of adjacent turbines is selected as a comparison standard. Since the wind farm environment remains unchanged, the comparison standard possesses sufficient stability. By integrating the spatial correlation weights between the benchmark turbine and the test turbine with historical data similarity, a dynamic benchmark is constructed. This benchmark changes in real time with wind conditions, eliminating the performance influence of the test turbines themselves and solving the problem of difficulty in quantitative evaluation after wind speed and direction sensor replacement.

[0008] The present invention is implemented using the following technical solutions:

[0009] A method for verifying the performance of wind speed and direction sensors for wind turbine units is proposed, including:

[0010] S1: For the test unit, select a benchmark unit to verify its performance based on the constraints.

[0011] S2: Collect verification data according to the wind speed segmentation requirements within a set time period; the verification data is the potential power generation of the wind turbine.

[0012] S3: Calculate a dynamic benchmark for performance verification based on the spatial correlation weights between the benchmark unit and the test unit;

[0013] S4: Perform a multi-dimensional evaluation of the replaced wind speed and direction sensors based on dynamic benchmarks.

[0014] In some embodiments of the present invention, the constraints are as follows:

[0015] ;in For testing the unit, As the benchmark unit, The diameter of the wind turbine, Wheel hub height;

[0016] In some embodiments of the present invention, the set duration is dynamically adjusted according to the turbulence intensity:

[0017] .

[0018] In some embodiments of the present invention, the wind speed segmentation requirements are as follows:

[0019] The wind speed is between 3 and 5 m / s, accounting for ≥20% of the data; the data collected in this wind speed range is located in the linear region of the power curve.

[0020] The wind speed range is 5-9 m / s, accounting for ≥35% of the data; the data collected in this wind speed range is located in the optimal power capture zone.

[0021] The wind speed range is 9-25 m / s, accounting for ≥25% of the data; the data collected within this wind speed range is located in the full-capacity operation zone.

[0022] In some embodiments of the present invention, S3 includes constructing a spatial correlation weight calculation model:

[0023] ;

[0024] in, ; yes and The overall covariance, For testing units The historical potential power generation, As a benchmark unit The historical potential power generation capacity; and These represent the test units. and benchmark units The historical overall standard deviation.

[0025] In some embodiments of the present invention, S3 includes constructing a dynamic benchmark model using spatial correlation weights:

[0026] ;in, This represents the potential power generation of the benchmark unit.

[0027] In some embodiments of the present invention, S3 further includes a benchmark validity verification step, comprising:

[0028] In dynamic benchmark conformity The benchmark can be enabled at any time; among which, As a reference after sensor replacement, This serves as a reference before the sensor is replaced.

[0029] In some embodiments of the present invention, the multidimensional evaluation of S4 includes:

[0030] When relative performance improvement rate And the benchmark stability coefficient This indicates a significant performance improvement;

[0031] when At 95% of the time, if This indicates that the performance remains unchanged;

[0032] when When this happens, the fault diagnosis protocol needs to be re-verified and restarted;

[0033] in, For relative performance improvement rate, To characterize the performance of the test unit after sensor replacement: , To test the potential power generation of the unit after replacing the sensor; Performance characteristics of the test unit before sensor replacement: , To test the potential power generation of the unit before replacing the sensor;

[0034] The baseline stability coefficient;

[0035] For data confidence, where, The number of valid data points. This represents the total number of data collected.

[0036] In some embodiments of the present invention, the method further includes:

[0037] If the selected benchmark unit In the event of a malfunction, the following model will be used to replace the unit:

[0038] ;

[0039] in, ; This represents the absolute value of the wind speed deviation. The absolute value of the wind direction deviation; when the data confidence level Automatically extend the data collection time. sky.

[0040] A wind turbine wind speed and direction sensor performance verification system is proposed, comprising several wind turbines, including:

[0041] The turbine selection unit is used to select a benchmark turbine from several wind turbines to verify the performance of the test turbine based on constraints.

[0042] The data acquisition unit is used to collect the potential power generation of the test unit and the benchmark unit according to the wind speed segment requirements within a set time period;

[0043] The dynamic benchmark determination unit is used to calculate a dynamic benchmark for performance verification based on the spatial correlation weight of the benchmark unit.

[0044] The multi-dimensional performance verification unit is used to perform multi-dimensional performance verification on the replaced wind speed and direction sensors based on dynamic benchmarks.

[0045] Compared with the prior art, the advantages and positive effects of the present invention include:

[0046] (1) For the test unit, a reference unit that is spatially related and temporally synchronized with it is selected based on the constraints. These reference units are in the same wind field environment as the test unit. Using these units as the reference can eliminate the interference of wind field fluctuations in time and improve the ability to suppress environmental interference.

[0047] (2) Using potential power generation as the verification object, this data can reflect the ability of wind speed and wind direction measurements to capture the unit, making the assessment more intuitive.

[0048] (3) By integrating the spatial correlation weights of the benchmark unit and the test unit with the similarity of historical data, a dynamic benchmark was constructed. This benchmark changes in real time with the wind conditions, which can eliminate the performance influence of the test unit itself and solve the problem of difficulty in quantitative evaluation after the replacement of wind speed and direction sensors.

[0049] (4) By weighted fusion of data from multiple benchmark units, resource complementarity is achieved compared with the verification method of historical data from a single unit, making the verification process more stable.

[0050] (5) Verification data is collected by wind speed segmentation to comprehensively cover the performance of the sensor in different wind speed ranges.

[0051] (6) Multidimensional evaluation provides a deeper and more refined verification capability.

[0052] Other features and advantages of the present invention will become clearer after reading the detailed description of the embodiments of the present invention in conjunction with the accompanying drawings. Attached Figure Description

[0053] The accompanying drawings, as part of this invention, are provided to further illustrate the invention. The illustrative embodiments and descriptions are used to explain the invention but do not constitute an undue limitation thereof. Clearly, the drawings described below are merely some embodiments; those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0054] Figure 1 The steps of the wind turbine wind speed and direction sensor performance verification method proposed in this invention are as follows;

[0055] Figure 2 The structure of the wind turbine wind speed and direction sensor performance verification system proposed in this invention is shown. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments will be clearly and completely described below with reference to the accompanying drawings. The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0057] like Figure 1 As shown, the wind speed and direction sensor performance verification method for wind turbines proposed in this invention includes:

[0058] S1: For the test unit, select a benchmark unit to verify its performance based on the constraints.

[0059] Test unit For the unit where the wind speed and direction sensors are being replaced. Reference unit. In order to test the unit Adjacent turbines located in the same wind farm, and the test turbine The following constraints must be met:

[0060] ;in, The diameter of the wind turbine, This refers to the wheel hub height.

[0061] S2: Collect verification data according to the wind speed segment requirements within the set time period.

[0062] The verification data represents the potential power generation of the test and benchmark units, and the set duration for data collection is dynamically adjusted based on the turbulence intensity.

[0063] .

[0064] Data was collected in segments based on wind speed:

[0065] (1) The wind speed is between 3-5 m / s, accounting for ≥20% of the data; the data collected in this wind speed range is located in the linear region of the power curve.

[0066] (2) The wind speed is between 5-9 m / s, accounting for ≥35% of the data; the data collected in this wind speed range is located in the optimal power capture zone.

[0067] (3) The wind speed is between 9 and 25 m / s, accounting for ≥25% of the data; the data collected in this wind speed range is located in the full-load operation area.

[0068] Remove outlier data: .

[0069] S3: Dynamic benchmark for performance verification based on spatial correlation weight calculation of the benchmark unit.

[0070] Construct a spatial correlation weight calculation model:

[0071] ;

[0072] in, ; yes and The overall covariance, For testing units The historical potential power generation, As a benchmark unit The historical potential power generation. and These represent the test units. and benchmark units Historical overall standard deviation; historical data requirements and data volume 1 year.

[0073] Constructing a dynamic benchmark using spatial correlation weights: ;

[0074] in, This represents the potential power generation of the benchmark unit.

[0075] Set the conditions for enabling the baseline to be valid: ; As a reference after sensor replacement, This serves as a reference before the sensor is replaced.

[0076] S4: Perform a multi-dimensional evaluation of the replaced wind speed and direction sensors based on dynamic benchmarks.

[0077] The evaluation parameters include:

[0078] (1) Relative performance improvement rate : ;when This indicates a significant performance improvement. Among them, To characterize the performance of the test unit after sensor replacement: , To test the potential power generation of the unit after replacing the sensor; Performance characteristics of the test unit before sensor replacement: , The potential power generation of the unit was tested before the sensor was replaced.

[0079] (2) Reference stability coefficient : ;when When the time is right, it indicates that the standard is met.

[0080] (3) Data confidence : ;when When this is the case, it indicates that the data is reliable. Among them, The number of valid data points. This represents the total number of data collected.

[0081] The evaluation criterion is: when the relative performance improvement rate And the benchmark stability coefficient When, it indicates a significant performance improvement; when At 95% of the time, if This indicates that performance remains unchanged and a verification report is generated; when At this time, it is necessary to re-verify and restart the fault diagnosis protocol.

[0082] During the aforementioned performance verification period, if the selected benchmark unit In the event of a malfunction, the following model will be used to replace the unit:

[0083] ;

[0084] in, ; This represents the absolute value of the wind speed deviation. This represents the absolute value of the wind direction deviation. When the data confidence level... Automatically extend the data collection time. sky.

[0085] like Figure 2 As shown, the present invention also proposes a wind turbine wind speed and direction sensor performance verification system, which includes several wind turbines, a benchmark turbine selection unit, a data acquisition unit, a dynamic benchmark model construction unit, and a multi-dimensional evaluation unit.

[0086] The turbine selection unit is used to select a benchmark turbine from several wind turbines to verify the performance of the test turbine based on constraints.

[0087] The data acquisition unit is used to collect the potential power generation of the test unit and the benchmark unit according to the wind speed segment requirements within a set time period.

[0088] The dynamic benchmark determination unit is used to calculate a dynamic benchmark for performance verification based on the spatial correlation weight of the benchmark unit.

[0089] The multi-dimensional performance verification unit is used to perform multi-dimensional performance verification on the replaced wind speed and direction sensors based on dynamic benchmarks.

[0090] The specific method for verifying the performance of the replaced wind speed and direction sensors has been described in detail and will not be repeated here.

[0091] The performance verification method proposed in this invention is described below with reference to a specific embodiment.

[0092] For a 200MW wind farm, wind turbine #G07 was selected as the test unit, meaning it was chosen to replace the wind speed and direction sensors. In this embodiment, all wind turbines have the same specifications, including the same rotor diameter. =136 meters.

[0093] According to step S1, the #G06 wind turbine unit, which is 312 meters away from it, and the #G08 wind turbine unit, which is 298 meters away from it, are selected as the benchmark units.

[0094] The potential power generation of the test unit and the benchmark unit was collected:

[0095] Table 1. Data Collection on Potential Power Generation of Test Units and Baseline Units

[0096] parameter 30 days before replacement 30 days after replacement Effective data rate α 96.7% 97.8% Percentage of speeds in the 5-8m / s range 38.2% 36.9% Number of times turbulence intensity exceeded the standard 3 times 2 times

[0097] Historical correlation is calculated based on the spatial correlation weighting algorithm model: , Calculate weights 5, Calculate the reference before replacement .

[0098] Perform performance verification:

[0099] Table 2 Performance Verification of Replacing Wind Speed ​​and Direction Sensors

[0100] index Before replacement After replacement <![CDATA[IP L ]]> 148,600 kWh 157,200 kWh Th <![CDATA[TH B =151,400 kWh]]> <![CDATA[TH A =152,100 kWh]]> G value <![CDATA[G B =98.15%]]> <![CDATA[G A =103.35%]]>

[0101] Verification conclusion: , The sensor performance was found to be significantly improved after replacement.

[0102] In other embodiments of the present invention, statistical analysis was conducted on measured data from eight wind farms, yielding the following technical comparison results:

[0103] Table 3 Comparison of the performance verification method of this invention with traditional performance verification methods

[0104]

[0105] It should be noted that the above description is not intended to limit the present invention, and the present invention is not limited to the examples given above. Any changes, modifications, additions or substitutions made by those skilled in the art within the scope of the present invention should also fall within the protection scope of the present invention.

Claims

1. A method for verifying the performance of a wind speed and direction sensor for a wind turbine generator, characterized in that, include: S1: For the test unit, select a benchmark unit to verify its performance based on the constraints. S2: Collect verification data according to the wind speed segmentation requirements within a set time period; the verification data is the potential power generation of the wind turbine. S3: Dynamic benchmark for performance verification based on spatial weight calculation of the benchmark unit; S4: Perform a multi-dimensional evaluation of the replaced wind speed and direction sensors based on dynamic benchmarks.

2. The method for verifying the performance of wind speed and direction sensors for wind turbine units according to claim 1, characterized in that, The constraints are as follows: ;in For testing the unit, As the benchmark unit, The diameter of the wind turbine, This refers to the wheel hub height.

3. The method for verifying the performance of wind speed and direction sensors for wind turbine units according to claim 1, characterized in that, The set duration is dynamically adjusted based on the turbulence intensity: 。 4. The method for verifying the performance of wind speed and direction sensors for wind turbine units according to claim 1, characterized in that, The wind speed segmentation requirements are as follows: The wind speed is between 3 and 5 m / s, accounting for ≥20% of the data; the data collected in this wind speed range is located in the linear region of the power curve. The wind speed range is 5-9 m / s, accounting for ≥35% of the data; the data collected in this wind speed range is located in the optimal power capture zone. The wind speed range is 9-25 m / s, accounting for ≥25% of the data; the data collected within this wind speed range is located in the full-capacity operation zone.

5. The method for verifying the performance of wind speed and direction sensors for wind turbine units according to claim 1, characterized in that, S3 includes the construction of a spatial weight calculation model: ； in, ; yes and The overall covariance, For testing units The historical potential power generation, As a benchmark unit The historical potential power generation capacity; and These represent the test units. and benchmark units The historical overall standard deviation.

6. The method for verifying the performance of wind speed and direction sensors for wind turbine units according to claim 5, characterized in that, S3 includes constructing a dynamic benchmark model using spatial weights: ;in, This represents the potential power generation of the benchmark unit.

7. The method for verifying the performance of wind speed and direction sensors for wind turbine units according to claim 6, characterized in that, S3 also includes a benchmark validity verification step, including: In dynamic benchmark conformity The benchmark can be enabled at any time; among which, As a reference after sensor replacement, This serves as a reference before the sensor is replaced.

8. The method for verifying the performance of wind speed and direction sensors for wind turbine units according to claim 7, characterized in that, S4's multidimensional assessment includes: When relative performance improvement rate And the benchmark stability coefficient This indicates a significant performance improvement; when At 95% of the time, if This indicates that the performance remains unchanged; when When this happens, the fault diagnosis protocol needs to be re-verified and restarted; in, For relative performance improvement rate, To characterize the performance of the test unit after sensor replacement: , To test the potential power generation of the unit after replacing the sensor; Performance characteristics of the test unit before sensor replacement: , To test the potential power generation of the unit before replacing the sensor; The baseline stability coefficient; For data confidence, where, The number of valid data points. This represents the total number of data collected.

9. The method for verifying the performance of wind speed and direction sensors for wind turbine units according to claim 6, characterized in that, The method further includes: If the selected benchmark unit In the event of a malfunction, the following model will be used to replace the unit: ； in, ; This represents the absolute value of the wind speed deviation. The absolute value of the wind direction deviation; when the data confidence level Automatically extend the data collection time. sky.

10. A wind turbine wind speed and direction sensor performance verification system, comprising several wind turbines, characterized in that, include: The turbine selection unit is used to select a benchmark turbine from several wind turbines to verify the performance of the test turbine based on constraints. The data acquisition unit is used to collect the potential power generation of the test unit and the benchmark unit according to the wind speed segment requirements within a set time period; The dynamic benchmark determination unit is used to calculate the dynamic benchmark for performance verification based on the spatial weight of the benchmark unit. The multi-dimensional performance verification unit is used to perform multi-dimensional performance verification on the replaced wind speed and direction sensors based on dynamic benchmarks.

Images