Method, device and equipment for detecting performance of wind turbine generator

Abstract

The present disclosure relates to a wind turbine performance detection method, device and equipment. The method comprises: dividing the wind turbine into multiple operating states according to operating parameters of the wind turbine, wherein the operating parameters include impeller rotating speed and pitch angle; determining power generation performance indicators of the wind turbine according to operating data corresponding to the multiple operating states; and determining performance of the wind turbine according to the performance indicators of the wind turbine, wherein the performance indicators include the power generation performance indicators. In this way, the power generation performance indicators of the wind turbine are determined according to the characteristics of the impeller rotating speed and the pitch angle, so that the power generation performance indicators determined under ideal impeller rotating speed and pitch angle are more accurate and can better reflect the real power generation performance, thereby further determining accurate performance indicators of the wind turbine.

Description

Technical Field

[0001] This disclosure relates to the field of wind power energy system control technology, specifically to a method, apparatus, and equipment for testing the performance of wind turbine generators. Background Technology

[0002] A wind turbine (or simply wind power unit) is a system that converts the kinetic energy of wind into electrical energy. A wind turbine consists of a rotor and a generator. The rotor comprises blades, a hub, and reinforcing components. The blades rotate under wind power, driving the generator head to rotate and generate electricity.

[0003] As wind turbines operate for longer periods, various components experience wear and tear to varying degrees. Damage to either electrical or mechanical equipment can lead to direct economic losses, especially with major components causing significant losses. Different wind turbines have been put into operation at different times, resulting in variations in grid connection years, turbine models, spare parts types, regional differences, and the maintenance and management levels of wind farms. Therefore, the wind power industry urgently needs an objective and widely applicable method for evaluating turbine performance to efficiently assess wind turbines. Summary of the Invention

[0004] The purpose of this disclosure is to provide a method, apparatus, and equipment for testing the performance of wind turbine generators, which can objectively and efficiently determine the performance of wind turbine generators.

[0005] To achieve the above objectives, this disclosure provides a performance testing method for wind turbine generators, the method comprising:

[0006] The wind turbine is divided into multiple operating states based on its operating parameters, including rotor speed and blade pitch angle.

[0007] Based on the operating data corresponding to the multiple operating states, the power generation performance indicators of the wind turbine are determined;

[0008] The performance of the wind turbine is determined based on its performance indicators, wherein the performance indicators include the power generation performance indicators.

[0009] Optionally, the operating states based on the rotor speed of the wind turbine include: a first state where the rotor speed is less than the grid connection speed; a second state where the rotor speed is greater than the grid connection speed but less than the rated speed; and a third state where the rotor speed is the rated speed.

[0010] The operating states, based on the pitch angle of the wind turbine, include: power generation operation state and power curtailment operation state.

[0011] Optionally, determining the power generation performance indicators of the wind turbine based on the operating data corresponding to the multiple operating states includes:

[0012] Based on the operating data corresponding to the multiple operating states, the following power generation performance indicators are determined:

[0013] E1 = K1·AEP below_rated / AEP_belowrated farm_avg

[0014] E2 = K1·AEP below_rated / AEP_belowrated farm_optimal

[0015] E3 = K1·AEP normal / AEP_normal farm_avg

[0016] E4 = K1·AEP normal / AEP_normal farm_optimal

[0017] Among them, E1 is the first power generation performance indicator, E2 is the second power generation performance indicator, E3 is the third power generation performance indicator, E4 is the fourth power generation performance indicator, and AEP is the fourth power generation performance indicator. below_rated The annual power generation corresponding to the operating data of the wind turbine simultaneously meeting the second state and the power generation operation state; AEP normal AEP_belowrated represents the annual power generation corresponding to the operating data of the wind turbine simultaneously satisfying the second state and the power generation operating state, as well as simultaneously satisfying the third state and the power generation operating state. farm_avg This refers to the annual power generation corresponding to the average power curve within the wind turbine group to which the wind turbine belongs, in the range below the rated power. The average power curve represents the relationship between the average power of each wind turbine in the wind turbine group and the wind speed. (AEP_belowrated) farm_optimal This refers to the annual power generation corresponding to the optimal power curve within the wind turbine group to which the wind turbine belongs, in the range below the rated power. The optimal power curve represents the relationship between the maximum power of each wind turbine in the wind turbine group and the wind speed. (AEP_normal) farm_avg AEP_normal represents the annual power generation corresponding to the average power curve of the wind turbine group within the entire wind speed range. farm_optimal K1 is the annual power generation corresponding to the optimal power curve within the entire wind speed range under the wind turbine group to which the wind turbine belongs. K1 is the first constant. The wind turbine group is a group of wind turbines of the same model in the same wind farm.

[0018] Optionally, the method further includes:

[0019] Based on the operating data of the wind turbine, the following indicators are determined: turbine dispersion index, data quality index, and turbine consistency index. The performance indicators further include the turbine dispersion index, the data quality index, and the turbine consistency index.

[0020] Optionally, the dispersion index of the unit can be determined according to the following method:

[0021] D = K2·(Dispersion) turbine -Dispersion min ) / Dispersion max

[0022] Where D is the dispersion index of the unit, Dispersion turbine Dispersion is the standard deviation of the scatter plot of actual operating data and the actual power curve for each wind turbine in the wind turbine group. min Dispersion is the minimum standard deviation of each wind turbine in the wind turbine group. max K1 represents the maximum standard deviation of each wind turbine in the wind turbine group, and K2 is the second constant.

[0023] Optionally, the data quality indicators are determined according to the following method:

[0024] Q1 = N exceed / N actual

[0025] Q2 = AEP exceed / AEP actual

[0026] Where Q1 is the first data quality indicator, Q2 is the second data quality indicator, and N exceed N represents the number of data points corresponding to operating points that exceed the thrust curve among the collected data points of the wind turbine. actual The total number of data points actually collected, AEP exceed For the annual power generation corresponding to the operating point exceeding the thrust curve among the collected data points of the wind turbine, AEP actual This represents the annual power generation corresponding to the actual data points collected.

[0027] Optionally, the unit consistency index is determined according to the following method:

[0028] For each wind turbine, determine the area between the power characteristic curve corresponding to the operating data that simultaneously satisfies the second state and the power generation operation state and the power characteristic curve below the rated power in the wind turbine group.

[0029] For each wind turbine group, the standard deviation of the area is used as the consistency index of the turbine group.

[0030] Optionally, determining the performance of the wind turbine based on multiple performance indicators includes:

[0031] For each performance indicator, the weight of the performance indicator is determined using the analytic hierarchy process (AHP) to obtain the first reference weight.

[0032] For each performance metric, the entropy weight method is used to determine the weight of the performance metric, thus obtaining the second reference weight;

[0033] For each performance metric, a target weight is determined based on the first reference weight and the second reference weight.

[0034] The performance of the wind turbine is determined based on multiple performance indicators and the determined target weights.

[0035] Optionally, determining the target weight of each performance metric based on the first reference weight and the second reference weight includes:

[0036] For each performance metric, the target weight of the performance metric is determined according to the following method:

[0037]

[0038] Among them, R i U is the target weight for the i-th performance metric. i M is the first reference weight for the i-th performance metric. i is the second reference weight for the i-th performance metric, and m is the number of the performance metrics.

[0039] This disclosure also provides a performance testing device for wind turbine generators, the device comprising:

[0040] The division module is used to divide the wind turbine into multiple operating states based on the operating parameters of the wind turbine, including rotor speed and blade pitch angle.

[0041] The first determining module is used to determine the power generation performance indicators of the wind turbine based on the operating data corresponding to the multiple operating states.

[0042] The second determining module is used to determine the performance of the wind turbine based on the performance indicators of the wind turbine, wherein the performance indicators include the power generation performance indicators.

[0043] Optionally, the operating states based on the rotor speed of the wind turbine include: a first state where the rotor speed is less than the grid connection speed; a second state where the rotor speed is greater than the grid connection speed but less than the rated speed; and a third state where the rotor speed is the rated speed.

[0044] The operating states, based on the pitch angle of the wind turbine, include: power generation operation state and power curtailment operation state.

[0045] Optionally, the first determining module is used to:

[0046] Based on the operating data corresponding to the multiple operating states, the following power generation performance indicators are determined:

[0047] E1 = K1·AEP below_rated / AEP_belowrated farm_avg

[0048] E2 = K1·AEP below_rated / AEP_belowrated farm_optimal

[0049] E3 = K1·AEP normal / AEP_normal farm_avg

[0050] E4 = K1·AEP normal / AEP_normal farm_optimal

[0051] Among them, E1 is the first power generation performance indicator, E2 is the second power generation performance indicator, E3 is the third power generation performance indicator, E4 is the fourth power generation performance indicator, and AEP is the fourth power generation performance indicator. below_rated The annual power generation corresponding to the operating data of the wind turbine simultaneously meeting the second state and the power generation operation state; AEP normal AEP_belowrated represents the annual power generation corresponding to the operating data of the wind turbine simultaneously satisfying the second state and the power generation operating state, as well as simultaneously satisfying the third state and the power generation operating state. farm_avg This refers to the annual power generation corresponding to the average power curve within the wind turbine group to which the wind turbine belongs, in the range below the rated power. The average power curve represents the relationship between the average power of each wind turbine in the wind turbine group and the wind speed. (AEP_belowrated) farm_optimal This refers to the annual power generation corresponding to the optimal power curve within the wind turbine group to which the wind turbine belongs, in the range below the rated power. The optimal power curve represents the relationship between the maximum power of each wind turbine in the wind turbine group and the wind speed. (AEP_normal) farm_avgAEP_normal represents the annual power generation corresponding to the average power curve of the wind turbine group within the entire wind speed range. farm_optimal K1 is the annual power generation corresponding to the optimal power curve within the entire wind speed range under the wind turbine group to which the wind turbine belongs. K1 is the first constant. The wind turbine group is a group of wind turbines of the same model in the same wind farm.

[0052] Optionally, the device further includes:

[0053] The third determining module is used to determine the unit dispersion index, data quality index and unit consistency index based on the operating data of the wind turbine unit. The performance index further includes the unit dispersion index, the data quality index and the unit consistency index.

[0054] Optionally, the third determining module is used to determine the unit dispersion index according to the following method:

[0055] D = K2·(Dispersion) turbine -Dispersion min ) / Dispersion max

[0056] Where D is the dispersion index of the unit, Dispersion turbine Dispersion is the standard deviation of the scatter plot of actual operating data and the actual power curve for each wind turbine in the wind turbine group. min Dispersion is the minimum standard deviation of each wind turbine in the wind turbine group. max K1 represents the maximum standard deviation of each wind turbine in the wind turbine group, and K2 is the second constant.

[0057] Optionally, the third determining module is used to determine the data quality indicators according to the following method:

[0058] Q1 = N exceed / N actual

[0059] Q2 = AEP exceed / AEP actual

[0060] Where Q1 is the first data quality indicator, Q2 is the second data quality indicator, and N exceed N represents the number of data points corresponding to operating points that exceed the thrust curve among the collected data points of the wind turbine. actual The total number of data points actually collected, AEP exceedFor the annual power generation corresponding to the operating point exceeding the thrust curve among the collected data points of the wind turbine, AEP actual This represents the annual power generation corresponding to the actual data points collected.

[0061] Optionally, the third determining module is used to determine the unit consistency index according to the following method:

[0062] For each wind turbine, determine the area between the power characteristic curve corresponding to the operating data that simultaneously satisfies the second state and the power generation operation state and the power characteristic curve below the rated power in the wind turbine group.

[0063] For each wind turbine group, the standard deviation of the area is used as the consistency index of the turbine group.

[0064] Optionally, the second determining module includes:

[0065] The first determining submodule is used to determine the weight of each performance indicator using the analytic hierarchy process (AHP) to obtain the first reference weight.

[0066] The second determining submodule is used to determine the weight of each performance indicator using the entropy weight method to obtain the second reference weight.

[0067] The third determining submodule is used to determine the target weight of each performance indicator based on the first reference weight and the second reference weight.

[0068] The fourth determination submodule is used to determine the performance of the wind turbine based on multiple performance indicators of the wind turbine and the determined target weights.

[0069] Optionally, the third determining submodule is used for:

[0070] For each performance metric, the target weight of the performance metric is determined according to the following method:

[0071]

[0072] Among them, R i U is the target weight for the i-th performance metric. i M is the first reference weight for the i-th performance metric. i is the second reference weight for the i-th performance metric, and m is the number of the performance metrics.

[0073] This disclosure also provides an electronic device, including:

[0074] A memory on which computer programs are stored;

[0075] A processor is configured to execute the computer program in the memory to implement the steps of the method described above provided in this disclosure.

[0076] The above technical solution divides wind turbine units into multiple operating states based on rotor speed and pitch angle. Power generation performance indicators are determined using the corresponding operating data for these states, and the overall performance of the wind turbine unit is determined based on these performance indicators, including power generation performance indicators. In this way, by determining the power generation performance indicators of the wind turbine unit based on the characteristics of rotor speed and pitch angle, the power generation performance indicators determined under ideal rotor speed and pitch angle are more accurate and better reflect the true power generation performance, thereby further determining the accurate performance indicators of the wind turbine unit.

[0077] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0078] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings:

[0079] Figure 1 This is a flowchart of a performance testing method for wind turbine generators provided in an exemplary embodiment.

[0080] Figure 2 This is a block diagram of a performance testing device for a wind turbine provided in an exemplary embodiment.

[0081] Figure 3 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0082] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0083] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.

[0084] Figure 1 This is a flowchart illustrating a performance testing method for a wind turbine generator as provided in an exemplary embodiment. Figure 1 As shown, the method includes steps S101 to S103.

[0085] In step S101, the wind turbine is divided into multiple operating states according to its operating parameters, including rotor speed and blade pitch angle.

[0086] The operating conditions can be divided into two sets: one based on impeller speed and the other on pitch angle. Alternatively, they can be divided into two sets based on impeller speed and the other on pitch angle. For example, the division can be based on characteristic values ​​of either impeller speed or pitch angle. These characteristic values ​​could be rated values ​​or predetermined values ​​set based on experiments or experience.

[0087] In step S102, the power generation performance indicators of the wind turbine are determined based on the operating data corresponding to multiple operating states.

[0088] The power generation performance indicators of wind turbines are used to characterize the degree of power generation performance of wind turbines. These performance indicators can be represented numerically, with higher numbers indicating better performance. Operating data can include parameters such as operating time, rotor speed, blade pitch angle, wind speed, and power output.

[0089] Current transformers can be pre-installed at the locations where monitoring is needed to collect operational data. Operating parameters can then be calculated from the collected current values, with a data sampling frequency of at least once every 10 minutes. Alternatively, the required operational data can be directly obtained from a Supervisory Control and Data Acquisition (SCADA) system.

[0090] In step S103, the performance of the wind turbine is determined based on its performance indicators, including power generation performance indicators.

[0091] Performance indicators are comprehensive metrics for evaluating the quality of wind turbine generators. Besides power generation performance indicators, performance indicators may also include other metrics, such as stability indicators that characterize the performance stability of wind turbine generators and consistency indicators that characterize the performance consistency of wind turbine generators of the same model.

[0092] The above technical solution divides wind turbine units into multiple operating states based on rotor speed and pitch angle. Power generation performance indicators are determined using the corresponding operating data for these states, and the overall performance of the wind turbine unit is determined based on these performance indicators, including power generation performance indicators. In this way, by determining the power generation performance indicators of the wind turbine unit based on the characteristics of rotor speed and pitch angle, the power generation performance indicators determined under ideal rotor speed and pitch angle are more accurate and better reflect the true power generation performance, thereby further determining the accurate performance indicators of the wind turbine unit.

[0093] In another embodiment, the operating states based on the rotor speed of the wind turbine may include: a first state where the rotor speed is less than the grid connection speed; a second state where the rotor speed is greater than the grid connection speed but less than the rated speed; and a third state where the rotor speed is the rated speed. The rated speed of the rotor is greater than the rotor speed when connected to the grid.

[0094] The operating status based on the pitch angle of the wind turbine can include: power generation operation status and power curtailment operation status.

[0095] Specifically, feature values ​​can be extracted from historical operating data of unit torque-power data and pitch angle-power data. The feature values ​​of rotor speed can include the rotor speed when connected to the grid and the rated rotor speed. Operating data under each time tag can be divided into corresponding operating states, and the operating data can be tagged one by one according to the operating state. Power generation operating state and power curtailment operating state can be distinguished based on the feature values ​​of the pitch angle.

[0096] Operating status can also include abnormal data status. Characteristic values ​​can be set for impeller speed and blade pitch angle based on expert experience to classify abnormal data status.

[0097] In this embodiment, the operating state of the wind turbine is divided according to the characteristic values ​​of the impeller speed and the pitch angle, respectively, so that the accuracy of the divided operating state is higher.

[0098] In another embodiment, the power generation performance indicators of the wind turbine are determined based on operating data corresponding to multiple operating states, including:

[0099] Based on the operating data corresponding to multiple operating states, the following power generation performance indicators are determined:

[0100] E1 = K1·AEP below_rated / AEP_belowrated farm_avg

[0101] E2 = K1·AEP below_rated / AEP_belowrated farm_optimal

[0102] E3 = K1·AEP normal / AEP_normal farm_avg

[0103] E4 = K1·AEP normal / AEP_normal farm_optimal

[0104] Among them, E1 is the first power generation performance indicator, E2 is the second power generation performance indicator, E3 is the third power generation performance indicator, and E4 is the fourth power generation performance indicator.

[0105] AEP below_rated The annual power generation corresponding to the operating data of the wind turbine simultaneously meeting the second state and the power generation operation state; AEP normal This refers to the annual power generation corresponding to the operating data of a wind turbine that simultaneously meets the second state and power generation operation state, as well as the third state and power generation operation state.

[0106] We can first calculate the power curve (GPC) corresponding to the operating data of the wind turbine that simultaneously meets the second state and the power generation operation state. below_rated Then calculate the corresponding annual power generation AEP. below_rated Furthermore, the power curves (GPC) corresponding to the operating data of the wind turbine simultaneously satisfying the second state and power generation operating state, as well as simultaneously satisfying the third state and power generation operating state, can be calculated first. normal Then calculate the corresponding annual power generation AEP. normal The power curve refers to the curve showing the relationship between the output power of a wind turbine and wind speed.

[0107] K1 is the first constant, for example, 100. A wind turbine group is a group of wind turbines of the same model within the same wind farm. A wind farm can have multiple models of wind turbines, and each model can have multiple wind turbines. Wind turbines of the same model within the same wind farm can be considered as a group.

[0108] AEP_belowrated farm_avg This refers to the annual power generation corresponding to the average power curve within the wind turbine group, specifically within the range below the rated power. The average power curve represents the relationship between the average power of each wind turbine in the group and the wind speed. AEP_belowrated farm_optimal This refers to the annual power generation corresponding to the optimal power curve within the wind turbine group, specifically within the range below the rated power. The optimal power curve represents the relationship between the maximum power of each wind turbine in the group and the wind speed. AEP_normal farm_avg This represents the annual power generation corresponding to the average power curve across the entire wind speed range for the wind turbine group to which the wind turbine belongs. AEP_normal farm_optimal This represents the annual power generation corresponding to the optimal power curve within the entire wind speed range for the wind turbine group to which the wind turbine belongs.

[0109] The system can preprocess the operating data of each wind turbine group under the management organization to meet the requirements of rotor speed / generator speed and blade pitch angle, and calculate the full-wind-speed power curve for each unit according to the IEC61400 method. It also performs average calculation on the power curve data for each wind speed bin interval, serving as the overall average reference power curve (GPC) for the entire field.avg ;

[0110] The system can preprocess the operating data of each wind turbine group under the management organization to meet the requirements of rotor speed / generator speed and blade pitch angle. It can also calculate the full-wind-speed power curve for each unit according to the IEC 61400 method. Furthermore, it can select the power curves of the top 5% to top 10% (maximum power) wind turbines in the group and average the power curve data for each wind speed bin interval to obtain the optimal reference power curve (GPC) for the entire field. optimal .

[0111] The field-wide average reference power curve (GPC) can be calculated based on the above calculation methods and in conjunction with the methods of IEC 61400. avg And the optimal reference power curve GPC optimal Furthermore, the above-mentioned index AEP_belowrated is calculated based on the overall wind frequency function. farm_avg AEP_belowrated farm_optimal AEP_normal farm_avg and AEP_normal farm_optimal。

[0112] In this embodiment, the power curves for the two stages above and below the rated power use calculation results from different sources, and based on the specific power generation performance indicators mentioned above, the power generation performance of the wind turbine is reflected from multiple perspectives, providing a comprehensive performance demonstration.

[0113] Before calculating the power generation performance indicators using the above method, anomaly assessment can be performed for each group using three methods: the 3-sigma principle, the median absolute deviation (MAD) method, and the Z-score method. If any one of these three methods determines a group is abnormal, then that group is classified as abnormal. Only if all three methods determine a group is normal is its group classified as normal. When calculating the power generation performance indicators, groups classified as abnormal can be excluded, and only data from normal groups can be used for calculation, thus increasing the accuracy of the power generation performance indicator calculation.

[0114] In another embodiment, the method further includes: determining the unit dispersion index, data quality index, and unit consistency index based on the wind turbine's operating data, wherein the performance index further includes the unit dispersion index, data quality index, and unit consistency index.

[0115] The unit dispersion index is used to characterize the performance differences of each wind turbine under different operating conditions. The data quality index is used to characterize the quality of the collected data. The unit consistency index is used to characterize the performance differences between different wind turbine groups.

[0116] In this embodiment, the performance of the wind turbine can be reflected by power generation performance indicators, turbine dispersion indicators, data quality indicators, and turbine consistency indicators, providing a comprehensive performance demonstration.

[0117] In another embodiment, the unit dispersion index is determined according to the following method:

[0118] D = K2·(Dispersion) turbine -Dispersion min ) / Dispersion max

[0119] Where D is the unit dispersion index, Dispersion turbine Dispersion is the standard deviation of the scatter plot of actual operating data for each wind turbine in the wind turbine group from the actual power curve. min Dispersion is the minimum standard deviation of each wind turbine in the wind turbine group. max K2 represents the maximum standard deviation of each wind turbine in the wind turbine group, and K2 is the second constant, for example, 100.

[0120] For example, the distance from each operating point to the actual power curve can be calculated, and then the standard deviation of each distance can be calculated. Using the above calculation formula, the relative performance differences between individual units within the same group can be quantified.

[0121] In yet another embodiment, data quality metrics are determined according to the following method:

[0122] Q1 = N exceed / N actual

[0123] Q2 = AEP exceed / AEP actual

[0124] Where Q1 is the first data quality indicator, Q2 is the second data quality indicator, and N exceed N represents the number of data points corresponding to operating points that exceed the thrust curve among the collected data points of the wind turbine. actual The total number of data points actually collected, AEP exceed For the annual power generation corresponding to the operating points of the wind turbines that exceed the thrust curve among the collected data points, AEP actualThis represents the annual power generation corresponding to the actual data points collected.

[0125] The total number of actual effective data points N of the wind turbine can be calculated using the wind turbine power superposition method. actual Compared with the actual annual power generation AEP actual Then, based on the swept area and thrust curve of the wind turbine, calculate the number N of data points corresponding to the operating points that exceed the thrust curve. exceed Actual annual power generation (AEP) exceeding the thrust curve exceed .

[0126] Specifically, according to Betz theory, since the energy extracted by wind turbines from natural wind is limited, the power loss can be explained as the rotational kinetic energy remaining in the wake. Theoretically, the maximum efficiency of a wind turbine is 0.593, and the maximum power it can generate at each wind speed range is:

[0127] P max i =0.593 / 2×AρV i (i = 1, 2, 3...)

[0128] Among them, P max i Let A be the maximum power generated by the wind turbine at wind speed range i, A be the area swept by the wind turbine rotor in one revolution, ρ be the atmospheric density, and V be the maximum power generated by the wind turbine at wind speed range i. i Let be the wind speed of the i-th wind speed segment.

[0129] The thrust coefficient determines the efficiency of a wind turbine. If the thrust coefficient is C... f Substituting this into the following formula, the maximum power that the wind turbine can generate at each wind speed range is:

[0130] P max i =C fi / 2×AρV i (i = 1, 2, 3...)

[0131] With (V1,P) max 1); (V2,P max 2); ...; (V i ,P max i The maximum guaranteed power characteristic curve is formed, and the scattered points above this curve are taken as the operating points that exceed the thrust curve.

[0132] In this embodiment, the data quality index is calculated using the above formula, which has high accuracy.

[0133] In yet another embodiment, the unit consistency index is determined according to the following method:

[0134] For each wind turbine, determine the area between the power characteristic curve corresponding to the operating data that simultaneously satisfies the second state and the power generation operation state and the power characteristic curve below the rated power in the wind turbine group.

[0135] For each wind turbine group, the standard deviation of the area is used as the unit consistency index.

[0136] In other words, within the range where the rotor speed is greater than the grid connection speed but less than the rated speed, calculate the power curve (GPC) for each wind turbine in a group. below_rated The power curve GPC of this group avg The area between wind farms is calculated, and then the standard deviation of the area is calculated for each wind farm and each group, serving as the unit consistency index for the wind farm. The unit consistency index of a group reflects the degree of consistency between that group and other groups.

[0137] In another embodiment, the performance of the wind turbine is determined based on multiple performance indicators, including:

[0138] For each performance indicator, the weight of the performance indicator is determined by the analytic hierarchy process (AHP) to obtain the first reference weight.

[0139] For each performance metric, the entropy weight method is used to determine the weight of the performance metric, thus obtaining the second reference weight;

[0140] For each performance metric, the target weight of the performance metric is determined based on the first reference weight and the second reference weight.

[0141] The performance of the wind turbine is determined based on multiple performance indicators and the established target weights.

[0142] The Analytic Hierarchy Process (AHP) reflects expert experience with different indicators, while entropy weighting reflects the information content characteristics provided by the data itself. Using both together not only reduces the subjectivity of AHP weighting but also minimizes weight fluctuations caused by data changes.

[0143] In this embodiment, both the analytic hierarchy process (AHP) and the entropy weight method are introduced, and their fusion is used to determine the weights of each performance indicator. This results in a more comprehensive weighted performance that better reflects the true characteristics of the data.

[0144] For each performance indicator, the min-max standardization method can be applied to standardize the data, transforming the absolute values ​​of each performance indicator into relative values ​​and eliminating the influence of units on the results. For n performance evaluation objects and m performance evaluation indicators, let x... ijThe score of the j-th performance index for the i-th performance evaluation object (i = 1, 2, ..., n; j = 1, 2, ..., m);

[0145] When normalizing heterogeneous indices, positive and negative indices can be normalized separately, as shown in the following formula:

[0146] Positive indicators

[0147] negative indicators

[0148] When calculating the entropy weight of each indicator: the entropy weight of the j-th performance evaluation indicator can be calculated according to the following formula:

[0149]

[0150] Among them, E j The entropy weight of the j-th performance evaluation index is represented; n is the total number of evaluation objects; p ij It is the weighted proportion of the value of the i-th performance evaluation object on the j-th performance metric relative to the scores of all objects to be evaluated on that metric:

[0151]

[0152] Where, x i ' j A positive index x can be used i ' j+ Or negative indicator x i ' j- You can choose according to your specific needs.

[0153] Determine the weight values ​​of each indicator: Obtain the information entropy weights (hereinafter referred to as the second reference weights) of each indicator according to the formula for calculating information entropy.

[0154]

[0155] Among them, M j This represents the entropy weight of the j-th performance metric.

[0156] The information weights (second reference weights) obtained by the entropy weight method can be expressed as:

[0157] M = [M1, M2, ..., M m ]

[0158] When determining the first reference weight using the Analytic Hierarchy Process (AHP), the performance indicators of each wind farm unit can be divided into several groups according to their correlation and membership relationships. Each group is defined as a layer, ultimately establishing a hierarchical system structure model composed of a top layer, intermediate layers, and a bottom layer. In the weight analysis of the intermediate layer to the top layer, a judgment matrix is ​​constructed based on the scoring principle of the 1-9 scale.

[0159] Subsequently, to verify the reasonableness of the results obtained by this method, a consistency check was performed on the judgment matrix. This matrix was generated through expert discussion and scoring. The first reference weight obtained by the analytic hierarchy process can be expressed as:

[0160] U = [U1, U2, ..., U m ]

[0161] For each performance metric, the target weight of the performance metric is determined based on the first reference weight and the second reference weight. This can include determining the target weight of the performance metric for each performance metric in the following manner:

[0162]

[0163] Among them, R i U is the target weight for the i-th performance metric. i M is the first reference weight for the i-th performance metric. i is the second reference weight for the i-th performance metric, and m is the number of performance metrics.

[0164] After determining the target weight for each performance indicator, for example, the values ​​of all performance indicators can be weighted and summed to obtain the final performance value of the wind turbine.

[0165] The performance evaluation of wind turbine units can be carried out according to a hierarchical structure, calculating the upper-level indicators layer by layer from bottom to top. This can be divided into two routes: from individual unit performance indicators to wind turbine model performance indicators, and from individual unit performance indicators to the overall performance indicators of the wind farm. This allows for the identification of performance anomalies in wind turbine units.

[0166] The above system can be directly embedded into an enterprise big data platform. The data acquisition module stores the data in a data warehouse, uses the methods disclosed herein to obtain the performance indicators of each unit as well as the performance indicators of different wind farms and turbine models, and stores the evaluation (testing) results in a relational database. The front-end page of the data platform can obtain the results from the relational database, display them in real time, and interact with the user.

[0167] The wind turbine performance testing method disclosed herein has a high degree of automation and low intervention from human and experience parameters. It can accurately extract the performance characteristic values ​​of the unit, locate the direction of anomalies, and improve the overall production capacity of enterprises.

[0168] Based on the same inventive concept, this disclosure also provides a performance testing device for wind turbine generators. Figure 2 This is a block diagram of a performance testing device for a wind turbine generator provided in an exemplary embodiment. Figure 2 As shown, the wind turbine performance testing device 200 includes a division module 201, a first determination module 202, and a second determination module 203.

[0169] The division module 201 is used to divide the wind turbine into multiple operating states based on the operating parameters of the wind turbine, including rotor speed and blade pitch angle.

[0170] The first determining module 202 is used to determine the power generation performance indicators of the wind turbine based on the operating data corresponding to multiple operating states.

[0171] The second determining module 203 is used to determine the performance of the wind turbine based on the performance indicators of the wind turbine, wherein the performance indicators include power generation performance indicators.

[0172] Optionally, the operating states based on the rotor speed of the wind turbine include: a first state where the rotor speed is less than the grid connection speed; a second state where the rotor speed is greater than the grid connection speed but less than the rated speed; and a third state where the rotor speed is the rated speed.

[0173] The operating states of wind turbines, based on their pitch angle, include: power generation operation state and power curtailment operation state.

[0174] Optionally, the first determining module 202 is used to: determine the following power generation performance indicators based on the operating data corresponding to multiple operating states:

[0175] E1 = K1·AEP below_rated / AEP_belowrated farm_avg

[0176] E2 = K1·AEP below_rated / AEP_belowrated farm_optimal

[0177] E3 = K1·AEP normal / AEP_normal farm_avg

[0178] E4 = K1·AEP normal / AEP_normal farm_optimal

[0179] Among them, E1 is the first power generation performance indicator, E2 is the second power generation performance indicator, E3 is the third power generation performance indicator, E4 is the fourth power generation performance indicator, and AEP is the fourth power generation performance indicator. below_ratedThe annual power generation corresponding to the operating data of the wind turbine simultaneously meeting the second state and the power generation operation state; AEP normal AEP_belowrated represents the annual power generation corresponding to the operating data of a wind turbine that simultaneously meets the second state and power generation operating state, as well as the third state and power generation operating state. farm_avg This refers to the annual power generation corresponding to the average power curve within the wind turbine group, specifically within the range below the rated power. The average power curve represents the relationship between the average power of each wind turbine in the group and the wind speed. (AEP_belowrated) farm_optimal This refers to the annual power generation corresponding to the optimal power curve within the wind turbine group, specifically within the range below the rated power. The optimal power curve represents the relationship between the maximum power of each wind turbine in the group and the wind speed. (AEP_normal) farm_avg For the wind turbine group, AEP_normal represents the annual power generation corresponding to the average power curve across the entire wind speed range. farm_optimal K1 represents the annual power generation corresponding to the optimal power curve within the entire wind speed range for the wind turbine group to which the wind turbine belongs. K1 is the first constant. The wind turbine group is a group of wind turbines of the same model in the same wind farm.

[0180] Optionally, the wind turbine performance testing device 200 also includes a third determining module.

[0181] The third determination module is used to determine the unit dispersion index, data quality index, and unit consistency index based on the wind turbine's operating data. Among them, the performance index also includes the unit dispersion index, data quality index, and unit consistency index.

[0182] Optionally, the third determining module is used to determine the unit dispersion index according to the following method:

[0183] D = K2·(Dispersion) turbine -Dispersion min ) / Dispersion max

[0184] Where D is the unit dispersion index, Dispersion turbine Dispersion is the standard deviation of the scatter plot of actual operating data for each wind turbine in the wind turbine group from the actual power curve. min Dispersion is the minimum standard deviation of each wind turbine in the wind turbine group. max K is the maximum value of the standard deviation of each wind turbine in the wind turbine group, and K2 is the second constant.

[0185] Optionally, the third determining module is used to determine data quality indicators in the following manner:

[0186] Q1 = N exceed / N actual

[0187] Q2 = AEP exceed / AEP actual

[0188] Where Q1 is the first data quality indicator, Q2 is the second data quality indicator, and N exceed N represents the number of data points corresponding to operating points that exceed the thrust curve among the collected data points of the wind turbine. actual The total number of data points actually collected, AEP exceed For the annual power generation corresponding to the operating points of the wind turbines that exceed the thrust curve among the collected data points, AEP actual This represents the annual power generation corresponding to the actual data points collected.

[0189] Optionally, the third determining module is used to determine the unit consistency index according to the following method:

[0190] For each wind turbine, determine the area between the power characteristic curve corresponding to the operating data that simultaneously satisfies the second state and the power generation operation state and the power characteristic curve below the rated power in the wind turbine group.

[0191] For each wind turbine group, the standard deviation of the area is used as the unit consistency index.

[0192] Optionally, the second determining module 203 includes a first determining submodule, a second determining submodule, a third determining submodule, and a fourth determining submodule.

[0193] The first determination submodule is used to determine the weight of each performance indicator using the analytic hierarchy process (AHP) to obtain the first reference weight.

[0194] The second determination submodule is used to determine the weight of each performance indicator using the entropy weight method, thus obtaining the second reference weight.

[0195] The third determination submodule is used to determine the target weight of each performance indicator based on the first reference weight and the second reference weight.

[0196] The fourth determination submodule is used to determine the performance of the wind turbine based on multiple performance indicators and the determined target weights.

[0197] Optionally, the third determining submodule is used to: determine the target weight of each performance metric according to the following method:

[0198]

[0199] Among them, R i U is the target weight for the i-th performance metric. i M is the first reference weight for the i-th performance metric. i is the second reference weight for the i-th performance metric, and m is the number of performance metrics.

[0200] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0201] The above technical solution divides wind turbine units into multiple operating states based on rotor speed and pitch angle. Power generation performance indicators are determined using the corresponding operating data for these states, and the overall performance of the wind turbine unit is determined based on these performance indicators, including power generation performance indicators. In this way, by determining the power generation performance indicators of the wind turbine unit based on the characteristics of rotor speed and pitch angle, the power generation performance indicators determined under ideal rotor speed and pitch angle are more accurate and better reflect the true power generation performance, thereby further determining the accurate performance indicators of the wind turbine unit.

[0202] This disclosure also provides an electronic device including a memory and a processor. The memory stores a computer program; the processor executes the computer program in the memory to implement the steps of the method described above.

[0203] Figure 3 This is a block diagram illustrating an electronic device 700 according to an exemplary embodiment. For example... Figure 3 As shown, the electronic device 700 may include a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0204] The processor 701 controls the overall operation of the electronic device 700 to complete all or part of the steps in the aforementioned wind turbine performance testing method. The memory 702 stores various types of data to support the operation of the electronic device 700. This data may include, for example, instructions for any application or method operating on the electronic device 700, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 702 or transmitted via communication component 705. The audio component also includes at least one speaker for outputting audio signals. I / O interface 704 provides an interface between processor 701 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G technologies, or combinations thereof, is not limited here. Therefore, the corresponding communication component 705 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0205] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the wind turbine performance testing method described above.

[0206] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the wind turbine performance testing method described above. For example, the computer-readable storage medium may be the memory 702 including program instructions described above, which may be executed by the processor 701 of the electronic device 700 to complete the wind turbine performance testing method described above.

[0207] In another exemplary embodiment, a computer program product is also provided, which includes a computer program executable by a programmable device, the computer program having a code portion for performing the above-described wind turbine performance testing method when executed by the programmable device.

[0208] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0209] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0210] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A performance testing method for wind turbine generators, characterized in that, The method includes: The wind turbine is divided into multiple operating states based on its operating parameters, including rotor speed and blade pitch angle. Based on the operating data corresponding to the multiple operating states, the power generation performance indicators of the wind turbine are determined; The performance of the wind turbine is determined based on its performance indicators, including the power generation performance indicators. The operating states of the wind turbine are divided according to its rotor speed, including: a first state where the rotor speed is less than the grid connection speed; a second state where the rotor speed is greater than the grid connection speed but less than the rated speed; and a third state where the rotor speed is the rated speed. The operating states of the wind turbine, as defined by its pitch angle, include: power generation operation state and power curtailment operation state. The step of determining the power generation performance indicators of the wind turbine based on the operating data corresponding to the multiple operating states includes: Based on the operating data corresponding to the multiple operating states, the following power generation performance indicators are determined: E1=K1•AEP below_rated / AEP_belowrated farm_avg E2=K1•AEP below_rated / AEP_belowrated farm_optimal E3=K1•AEP normal / AEP_normal farm_avg E4=K1•AEP normal / AEP_normal farm_optimal Among them, E1 is the first power generation performance indicator, E2 is the second power generation performance indicator, E3 is the third power generation performance indicator, E4 is the fourth power generation performance indicator, and AEP is the fourth power generation performance indicator. below_rated The annual power generation corresponding to the operating data of the wind turbine simultaneously meeting the second state and the power generation operation state; AEP normal AEP_belowrated represents the annual power generation corresponding to the operating data of the wind turbine simultaneously satisfying the second state and the power generation operating state, as well as simultaneously satisfying the third state and the power generation operating state. farm_avg This refers to the annual power generation corresponding to the average power curve within the wind turbine group to which the wind turbine belongs, in the range below the rated power. The average power curve represents the relationship between the average power of each wind turbine in the wind turbine group and the wind speed. (AEP_belowrated) farm_optimal This refers to the annual power generation corresponding to the optimal power curve within the wind turbine group to which the wind turbine belongs, in the range below the rated power. The optimal power curve represents the relationship between the maximum power of each wind turbine in the wind turbine group and the wind speed. (AEP_normal) farm_avg AEP_normal represents the annual power generation corresponding to the average power curve of the wind turbine group within the entire wind speed range. farm_optimal K1 is the annual power generation corresponding to the optimal power curve within the entire wind speed range under the wind turbine group to which the wind turbine belongs. K1 is the first constant. The wind turbine group is a group of wind turbines of the same model in the same wind farm.

2. The method according to claim 1, characterized in that, The method further includes: Based on the operating data of the wind turbine, the following indicators are determined: turbine dispersion index, data quality index, and turbine consistency index. The performance indicators further include the turbine dispersion index, the data quality index, and the turbine consistency index.

3. The method according to claim 2, characterized in that, The dispersion index of the generator set is determined according to the following method: D=K2•(Dispersion turbine -Dispersion min ) / Dispersion max Where D is the dispersion index of the unit, Dispersion turbine Dispersion is the standard deviation of the scatter plot of actual operating data and the actual power curve for each wind turbine in the wind turbine group. min Dispersion is the minimum standard deviation of each wind turbine in the wind turbine group. max K1 represents the maximum standard deviation of each wind turbine in the wind turbine group, and K2 is the second constant.

4. The method according to claim 2, characterized in that, The data quality indicators are determined according to the following method: Q1=N exceed / N actual Q2=AEP exceed / AEP actual Where Q1 is the first data quality indicator, Q2 is the second data quality indicator, and N exceed N represents the number of data points corresponding to operating points that exceed the thrust curve among the collected data points of the wind turbine. actual The total number of data points actually collected, AEP exceed For the annual power generation corresponding to the operating point exceeding the thrust curve among the collected data points of the wind turbine, AEP actual This represents the annual power generation corresponding to the actual data points collected.

5. The method according to claim 2, characterized in that, The unit consistency index is determined according to the following method: For each wind turbine, determine the area between the power characteristic curve corresponding to the operating data that simultaneously satisfies the second state and the power generation operation state and the power characteristic curve below the rated power in the wind turbine group. For each wind turbine group, the standard deviation of the area is used as the consistency index of the turbine group.

6. The method according to any one of claims 1-5, characterized in that, The step of determining the performance of the wind turbine based on multiple performance indicators includes: For each performance indicator, the weight of the performance indicator is determined using the analytic hierarchy process (AHP) to obtain the first reference weight. For each performance metric, the entropy weight method is used to determine the weight of the performance metric, thus obtaining the second reference weight; For each performance metric, a target weight is determined based on the first reference weight and the second reference weight. The performance of the wind turbine is determined based on multiple performance indicators and the determined target weights.

7. The method according to claim 6, characterized in that, The step of determining the target weight of each performance indicator based on the first reference weight and the second reference weight includes: For each performance metric, the target weight of the performance metric is determined according to the following method: in, For the first The target weight of each performance metric For the first The first reference weight for each performance metric For the first The second reference weight for each performance metric The number of the performance metrics.

8. A performance testing device for wind turbine generators, characterized in that, The device includes: The division module is used to divide the wind turbine into multiple operating states based on the operating parameters of the wind turbine, including rotor speed and blade pitch angle. The first determining module is used to determine the power generation performance indicators of the wind turbine based on the operating data corresponding to the multiple operating states. The second determining module is used to determine the performance of the wind turbine based on the performance indicators of the wind turbine, wherein the performance indicators include the power generation performance indicators. The operating states of the wind turbine generator are divided according to the rotor speed: a first state where the rotor speed is less than the grid connection speed, a second state where the rotor speed is greater than the grid connection speed but less than the rated speed, and a third state where the rotor speed is the rated speed. The operating states of the wind turbine, as defined by its pitch angle, include: power generation operation state and power curtailment operation state. The first determining module is used for: Based on the operating data corresponding to the multiple operating states, the following power generation performance indicators are determined: E1=K1•AEP below_rated / AEP_belowrated farm_avg E2=K1•AEP below_rated / AEP_belowrated farm_optimal E3=K1•AEP normal / AEP_normal farm_avg E4=K1•AEP normal / AEP_normal farm_optimal Among them, E1 is the first power generation performance indicator, E2 is the second power generation performance indicator, E3 is the third power generation performance indicator, E4 is the fourth power generation performance indicator, and AEP is the fourth power generation performance indicator. below_rated The annual power generation corresponding to the operating data of the wind turbine simultaneously meeting the second state and the power generation operation state; AEP normal AEP_belowrated represents the annual power generation corresponding to the operating data of the wind turbine simultaneously satisfying the second state and the power generation operating state, as well as simultaneously satisfying the third state and the power generation operating state. farm_avg This refers to the annual power generation corresponding to the average power curve within the wind turbine group to which the wind turbine belongs, in the range below the rated power. The average power curve represents the relationship between the average power of each wind turbine in the wind turbine group and the wind speed. (AEP_belowrated) farm_optimal This refers to the annual power generation corresponding to the optimal power curve within the wind turbine group to which the wind turbine belongs, in the range below the rated power. The optimal power curve represents the relationship between the maximum power of each wind turbine in the wind turbine group and the wind speed. (AEP_normal) farm_avg AEP_normal represents the annual power generation corresponding to the average power curve of the wind turbine group within the entire wind speed range. farm_optimal K1 is the annual power generation corresponding to the optimal power curve within the entire wind speed range under the wind turbine group to which the wind turbine belongs. K1 is the first constant. The wind turbine group is a group of wind turbines of the same model in the same wind farm.

9. The apparatus according to claim 8, characterized in that, The device further includes: The third determining module is used to determine the unit dispersion index, data quality index and unit consistency index based on the operating data of the wind turbine unit. The performance index further includes the unit dispersion index, the data quality index and the unit consistency index.

10. The apparatus according to claim 9, characterized in that, The third determining module is used to determine the unit dispersion index according to the following method: D=K2•(Dispersion turbine -Dispersion min ) / Dispersion max Where D is the dispersion index of the unit, Dispersion turbine Dispersion is the standard deviation of the scatter plot of actual operating data and the actual power curve for each wind turbine in the wind turbine group. min Dispersion is the minimum standard deviation of each wind turbine in the wind turbine group. max K1 represents the maximum standard deviation of each wind turbine in the wind turbine group, and K2 is the second constant.

11. The apparatus according to claim 9, characterized in that, The third determining module is used to determine the data quality indicators according to the following method: Q1=N exceed / N actual Q2=AEP exceed / AEP actual Where Q1 is the first data quality indicator, Q2 is the second data quality indicator, and N exceed N represents the number of data points corresponding to operating points that exceed the thrust curve among the collected data points of the wind turbine. actual The total number of data points actually collected, AEP exceed For the annual power generation corresponding to the operating point exceeding the thrust curve among the collected data points of the wind turbine, AEP actual This represents the annual power generation corresponding to the actual data points collected.

12. The apparatus according to claim 9, characterized in that, The third determining module is used to determine the unit consistency index according to the following method: For each wind turbine, determine the area between the power characteristic curve corresponding to the operating data that simultaneously satisfies the second state and the power generation operation state and the power characteristic curve below the rated power in the wind turbine group. For each wind turbine group, the standard deviation of the area is used as the consistency index of the turbine group.

13. The apparatus according to any one of claims 8-12, characterized in that, The second determining module includes: The first determining submodule is used to determine the weight of each performance indicator using the analytic hierarchy process (AHP) to obtain the first reference weight. The second determining submodule is used to determine the weight of each performance indicator using the entropy weight method to obtain the second reference weight. The third determining submodule is used to determine the target weight of each performance indicator based on the first reference weight and the second reference weight. The fourth determination submodule is used to determine the performance of the wind turbine based on multiple performance indicators of the wind turbine and the determined target weights.

14. The apparatus according to claim 13, characterized in that, The third determining submodule is used for: For each performance metric, the target weight of the performance metric is determined according to the following method: in, For the first The target weight of each performance metric For the first The first reference weight for each performance metric For the first The second reference weight for each performance metric The number of the performance metrics.

15. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method according to any one of claims 1-7.

Images