Wind turbine power curve fitting method, device and electronic equipment

Abstract

The present invention relates to a method, device and electronic device for fitting a power curve of a wind turbine generator set, the method comprising: obtaining the operation data of the wind turbine generator set including the real-time wind speed and the real-time active power within a set time period; taking the real-time wind speed as a reference object, combining the cut-in wind speed value of the wind turbine generator set, and dividing the real-time wind speed data into a plurality of wind speed intervals according to the set wind speed partition step; determining the lower limit power value and the upper limit power value of each wind speed interval; according to the lower limit power value and the upper limit power value of each wind speed interval, eliminating the abnormal real-time active power in the corresponding wind speed interval, and generating an effective active power data set; according to all the real-time wind speed data in each wind speed interval and the effective active power data set corresponding to each wind speed interval, fitting the power curve of the wind turbine generator set. The method can complete the cleaning of abnormal data by relying on the real-time wind speed and the real-time active power, so as to accurately fit the power curve of the wind turbine generator set.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine generator sets, and in particular to a method, a device and an electronic device for fitting a power curve of a wind turbine generator set. Background Art

[0002] The power curve of a wind turbine reflects the corresponding relationship between the output power of the wind turbine and the wind speed, and is one of the key indicators for measuring the performance of a wind turbine. During design and commissioning, wind turbine manufacturers generally provide a guaranteed power curve. However, in actual operation, wind turbines are affected by many factors such as the environment, operating status, and grid dispatch, which can lead to differences in the actual operating power curves of wind turbines at different points in the same wind farm. The actual operating power curve can reflect the operating status and power generation efficiency of the wind turbine. At the same time, combined with the wind speed distribution of the wind farm, the actual operating power curve is also used to predict power generation, so it is particularly important to accurately fit or calculate the power curve.

[0003] In the field of wind power, there are data or reports with various resolutions used to characterize the operating status of wind turbines, such as second-level data, minute data, 10-minute data, monthly data, and annual data. 10-minute data refers to dividing the operating time into several segments at intervals of 10 minutes, and then obtaining the average value, maximum value, minimum value, variance, etc. of relevant parameters (such as wind speed, wind direction, active power, reactive power, and temperature of each device) in each 10-minute interval. According to IEC and relevant international regulations, the power curve of wind turbines is fitted using the 10-minute average wind speed and average active power data of wind turbines during normal operation, and the relevant algorithms are used for fitting. Since wind turbines are inevitably prone to abnormal conditions such as faults, power-limited operation, and power-limited operation during operation, when fitting the power curve, the data points that do not meet the IEC requirements must be cleaned up first, and then the corresponding algorithms are used to fit the remaining data. Common methods include the IEC agreed Bin value method (also known as the interval method or bin method), the maximum probability density method, the probability density extreme value method, the maximum likelihood method, and the polynomial fitting method. However, the accuracy of these methods is heavily dependent on the elimination of abnormal data in the 10-minute operation data, such as eliminating power-limited operation data and fault period data in advance. At this time, it is often necessary to provide parameters such as blade angle, generator speed, wind turbine operation status, wind turbine power-limited status in the 10-minute operation data report to effectively eliminate abnormal data. However, for some wind turbines, especially those that are older, the 10-minute operation data report does not include the above parameters. At this time, it is very difficult to clean up abnormal data such as power-limited operation, which leads to poor accuracy of the fitted wind turbine power curve. Summary of the invention

[0004] The present invention aims to solve, at least to some extent, one of the technical problems in the related art that "the 10-minute operating data reports provided by some wind turbines, especially old wind turbines from earlier years, do not include parameters such as blade angle, generator speed, wind turbine operating status, and wind turbine power limit status, which makes it difficult to clean up abnormal data, and further leads to poor accuracy of the fitted wind turbine power curve."

[0005] To this end, the first purpose of the present invention is to propose a method for fitting a wind turbine power curve. This method does not require the wind turbine operation data report within a set time period to provide additional parameters such as the wind turbine operation status, wind turbine blade angle value, wind turbine generator speed, wind turbine power limit, etc. as the basis for data cleaning. Abnormal data can be cleaned by relying on real-time wind speed and real-time active power to accurately fit the power curve.

[0006] The second objective of the present invention is to provide a wind turbine power curve fitting device.

[0007] A third objective of the present invention is to provide an electronic device.

[0008] A fourth object of the present invention is to provide a computer-readable storage medium.

[0009] A fifth object of the present invention is to provide a computer program product.

[0010] To achieve the above-mentioned purpose, the first aspect of the embodiment of the present invention proposes a method for fitting a power curve of a wind turbine generator set, comprising: obtaining operating data of the wind turbine generator set within a set time period; wherein the operating data includes real-time wind speed and real-time active power; taking the real-time wind speed as a reference object, combined with the cut-in wind speed value of the wind turbine generator set, dividing the real-time wind speed data into multiple wind speed intervals according to the set wind speed partition step; determining the lower limit power value and the upper limit power value of each wind speed interval; according to the lower limit power value and the upper limit power value of each wind speed interval, eliminating the abnormal real-time active power in the corresponding wind speed interval, and generating an effective active power data set; fitting the power curve of the wind turbine generator set according to all real-time wind speed data in each wind speed interval and the effective active power data set corresponding to each wind speed interval.

[0011] According to the wind turbine power curve fitting method of the embodiment of the present invention, the operation data of the wind turbine including the real-time wind speed and the real-time active power within the set time length are first obtained, and the real-time wind speed is used as a reference object, combined with the cut-in wind speed value of the wind turbine, and the real-time wind speed data is divided into multiple wind speed intervals according to the set wind speed partition step, and then the lower limit power value and the upper limit power value of each wind speed interval are determined, and according to the lower limit power value and the upper limit power value of each wind speed interval, the abnormal real-time active power in the corresponding wind speed interval is eliminated, and an effective active power data set is generated, and finally, according to all the real-time wind speed data in each wind speed interval and the effective active power data set corresponding to each wind speed interval, the power curve of the wind turbine is fitted. Therefore, the method does not require the operation data report of the wind turbine within the set time length to provide additional parameters such as the wind turbine operation status, the wind turbine blade angle value, the wind turbine generator speed, and the wind turbine power limit as the basis for data cleaning, and the cleaning of abnormal data can be completed by relying on the real-time wind speed and the real-time active power, so as to accurately fit the power curve.

[0012] In addition, the wind turbine power curve fitting method proposed in the first aspect of the present invention may also have the following additional technical features:

[0013] According to an embodiment of the present invention, the real-time wind speed is used as a reference object, combined with the cut-in wind speed value of the wind turbine, and the real-time wind speed data is divided into multiple wind speed intervals according to a set wind speed partition step, including:

[0014] The lower limit wind speed value of the first wind speed interval among the multiple wind speed intervals is 0, and the upper limit wind speed value of the first wind speed interval is the cut-in wind speed value minus half of the set wind speed partition step;

[0015] The lower limit wind speed value of the i-th wind speed interval among the multiple wind speed intervals is the upper limit wind speed value of the i-1-th wind speed interval, and the upper limit wind speed value of the i-th wind speed interval is the upper limit wind speed value of the i-1-th wind speed interval plus the set wind speed partition step; wherein i is a positive integer greater than or equal to 2.

[0016] According to one embodiment of the present invention, determining a lower power limit value and an upper power limit value of a first wind speed interval includes:

[0017] Determine that the lower limit power value of the first wind speed interval is greater than 0;

[0018] An upper limit power value of the first wind speed interval is determined to be the theoretical active power corresponding to the cut-in wind speed value.

[0019] According to one embodiment of the present invention, the method further includes:

[0020] Calculate the ratio of the theoretical active power corresponding to the median wind speed value of the third wind speed interval to the theoretical active power corresponding to the cut-in wind speed value as the first value;

[0021] Calculate the cube of the ratio of the median wind speed value of the third wind speed interval to the cut-in wind speed value as the second value;

[0022] If the difference between the first value and the second value is greater than a set difference, the upper limit power value of the first wind speed interval is updated to the theoretical active power corresponding to the median wind speed value of the third wind speed interval.

[0023] According to one embodiment of the present invention, determining a lower limit power value and an upper limit power value of the i-th wind speed interval includes:

[0024] Sort the effective active powers in the effective active power data set corresponding to the i-1th wind speed interval from large to small, and obtain the effective active power value arranged at the first set percentage position as the lower limit power value of the i-th wind speed interval;

[0025] The upper limit power value of the i-th wind speed interval is determined according to the maximum effective active power in the effective active power data set corresponding to the i-1-th wind speed interval, the upper limit wind speed value of the i-1-th wind speed interval, the upper limit wind speed value of the i-th wind speed interval and the second set percentage.

[0026] According to one embodiment of the present invention, the determining the upper limit power value of the i-th wind speed interval according to the maximum effective active power in the effective active power data set corresponding to the i-1th wind speed interval, the upper limit wind speed value of the i-1th wind speed interval, the upper limit wind speed value of the i-th wind speed interval and the second set percentage includes:

[0027] Calculate the cube of the upper limit wind speed value of the (i-1)th wind speed interval as the third value;

[0028] Calculate the cube of the upper limit wind speed value of the i-th wind speed interval as the fourth value;

[0029] The ratio of the fourth value to the third value is used as the fifth value;

[0030] The product of the maximum effective active power in the effective active power data set corresponding to the i-1th wind speed interval, the fifth value and the second set percentage is used as the upper limit power value of the i-th wind speed interval.

[0031] According to an embodiment of the present invention, when the median wind speed value of the i-th wind speed interval is greater than the rated wind speed of the wind turbine generator set, the fifth value is 1.

[0032] According to an embodiment of the present invention, fitting the power curve of the wind turbine generator set according to all the real-time wind speed data in each of the wind speed intervals and the effective active power data set corresponding to each of the wind speed intervals includes:

[0033] Get the average wind speed of all real-time wind speed data in each wind speed interval;

[0034] Obtain the average power of the effective active power data set corresponding to each wind speed interval;

[0035] The power curve of the wind turbine generator set is obtained by fitting according to the average wind speed and the average power in each wind speed interval.

[0036] To achieve the above-mentioned purpose, the second aspect of the embodiment of the present invention proposes a wind turbine power curve fitting device, including: an acquisition module, used to obtain the operating data of the wind turbine within a set time period; wherein the operating data includes real-time wind speed and real-time active power; a division module, used to use the real-time wind speed as a reference object, combined with the cut-in wind speed value of the wind turbine, and divide the real-time wind speed data into multiple wind speed intervals according to the set wind speed partition step; a determination module, used to determine the lower limit power value and the upper limit power value of each wind speed interval; a removal module, used to remove the abnormal real-time active power in the corresponding wind speed interval according to the lower limit power value and the upper limit power value of each wind speed interval, and generate an effective active power data set; a fitting module, used to fit the power curve of the wind turbine according to each wind speed interval and the effective active power data set corresponding to each wind speed interval.

[0037] According to the wind turbine power curve fitting device of the embodiment of the present invention, the operation data of the wind turbine within the set time length is obtained by the acquisition module, and the operation data includes real-time wind speed and real-time active power. The real-time wind speed data is divided into multiple wind speed intervals according to the set wind speed partition step length by the division module with the real-time wind speed as the reference object and the cut-in wind speed value of the wind turbine. The lower limit power value and the upper limit power value of each wind speed interval are determined by the determination module. The abnormal real-time active power in the corresponding wind speed interval is eliminated according to the lower limit power value and the upper limit power value of each wind speed interval by the elimination module, and an effective active power data set is generated. The power curve of the wind turbine is fitted by the fitting module according to each wind speed interval and the effective active power data set corresponding to each wind speed interval. Therefore, the device does not need the operation data report of the wind turbine within the set time length to provide additional parameters such as the wind turbine operation status, the wind turbine blade angle value, the wind turbine generator speed, and the wind turbine power limit as the basis for data cleaning. The cleaning of abnormal data can be completed by relying on the real-time wind speed and real-time active power, so as to accurately fit the power curve.

[0038] In addition, the wind turbine power curve fitting device provided in the second aspect of the present invention may also have the following additional technical features:

[0039] According to an embodiment of the present invention, the division module is used to divide the real-time wind speed data into multiple wind speed intervals according to a set wind speed partition step, taking the real-time wind speed as a reference object and combining the cut-in wind speed value of the wind turbine generator set, including:

[0040] The lower limit wind speed value of the first wind speed interval among the multiple wind speed intervals is 0, and the upper limit wind speed value of the first wind speed interval is the cut-in wind speed value minus half of the set wind speed partition step;

[0041] The lower limit wind speed value of the i-th wind speed interval among the multiple wind speed intervals is the upper limit wind speed value of the i-1-th wind speed interval, and the upper limit wind speed value of the i-th wind speed interval is the upper limit wind speed value of the i-1-th wind speed interval plus the set wind speed partition step; wherein i is a positive integer greater than or equal to 2.

[0042] According to an embodiment of the present invention, when the determination module is used to determine the lower limit power value and the upper limit power value of the first wind speed interval, it includes:

[0043] Determine that the lower limit power value of the first wind speed interval is greater than 0;

[0044] An upper limit power value of the first wind speed interval is determined to be the theoretical active power corresponding to the cut-in wind speed value.

[0045] According to one embodiment of the present invention, the above device further includes:

[0046] An updating module is used to calculate the ratio of the theoretical active power corresponding to the median wind speed value of the third wind speed interval to the theoretical active power corresponding to the cut-in wind speed value as the first value, and calculate the cube of the ratio of the median wind speed value of the third wind speed interval to the cut-in wind speed value as the second value, and when the difference between the first value and the second value is greater than the set difference, update the upper limit power value of the first wind speed interval to the theoretical active power corresponding to the median wind speed value of the third wind speed interval.

[0047] According to an embodiment of the present invention, when the determination module is used to determine the lower limit power value and the upper limit power value of the i-th wind speed interval, it includes:

[0048] Sort the effective active powers in the effective active power data set corresponding to the i-1th wind speed interval from large to small, and obtain the effective active power value arranged at the first set percentage position as the lower limit power value of the i-th wind speed interval;

[0049] The upper limit power value of the i-th wind speed interval is determined according to the maximum effective active power in the effective active power data set corresponding to the i-1-th wind speed interval, the upper limit wind speed value of the i-1-th wind speed interval, the upper limit wind speed value of the i-th wind speed interval and the second set percentage.

[0050] According to one embodiment of the present invention, the determination module is used to determine the upper limit power value of the i-th wind speed interval according to the maximum effective active power in the effective active power data set corresponding to the i-1th wind speed interval, the upper limit wind speed value of the i-1th wind speed interval, the upper limit wind speed value of the i-th wind speed interval and the second set percentage, including:

[0051] Calculate the cube of the upper limit wind speed value of the (i-1)th wind speed interval as the third value;

[0052] Calculate the cube of the upper limit wind speed value of the i-th wind speed interval as the fourth value;

[0053] The ratio of the fourth value to the third value is used as the fifth value;

[0054] The product of the maximum effective active power in the effective active power data set corresponding to the i-1th wind speed interval, the fifth value and the second set percentage is used as the upper limit power value of the i-th wind speed interval.

[0055] According to an embodiment of the present invention, when the median wind speed value of the i-th wind speed interval is greater than the rated wind speed of the wind turbine generator set, the fifth value is 1.

[0056] According to an embodiment of the present invention, the fitting module is used to fit the power curve of the wind turbine according to all the real-time wind speed data in each of the wind speed intervals and the effective active power data set corresponding to each of the wind speed intervals, including:

[0057] Get the average wind speed of all real-time wind speed data in each wind speed interval;

[0058] Obtain the average power of the effective active power data set corresponding to each wind speed interval;

[0059] The power curve of the wind turbine generator set is obtained by fitting according to the average wind speed and the average power in each wind speed interval.

[0060] To achieve the above object, the third aspect of the present invention further provides an electronic device, including:

[0061] at least one processor; and

[0062] a memory communicatively connected to the at least one processor; wherein,

[0063] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned wind turbine power curve fitting method.

[0064] The battery device of the embodiment of the present invention executes the above-mentioned wind turbine power curve fitting method, so that there is no need for the wind turbine operation data report within a set time period to provide additional parameters such as the wind turbine operation status, wind turbine blade angle value, wind turbine generator speed, wind turbine power limit, etc. as the basis for data cleaning. Instead, the abnormal data can be cleaned by relying on real-time wind speed and real-time active power to accurately fit the power curve.

[0065] To achieve the above-mentioned purpose, a fourth aspect of the present invention further proposes a computer-readable storage medium, wherein the computer instructions are used to enable the computer to execute the above-mentioned wind turbine power curve fitting method.

[0066] The computer-readable storage medium of an embodiment of the present invention executes the above-mentioned wind turbine power curve fitting method, so that there is no need for the wind turbine operation data report within a set time period to provide additional parameters such as the wind turbine operation status, wind turbine blade angle value, wind turbine generator speed, wind turbine power limit, etc. as the basis for data cleaning. Instead, the cleaning of abnormal data can be completed by relying on real-time wind speed and real-time active power to accurately fit the power curve.

[0067] To achieve the above-mentioned purpose, a fifth aspect of the present invention further provides a computer program product, and when the instruction processor in the computer program product is executed, the above-mentioned wind turbine power curve fitting method is executed.

[0068] The computer program product of the embodiment of the present invention executes the above-mentioned wind turbine power curve fitting method, so that there is no need for the wind turbine operation data report within a set time period to provide additional parameters such as the wind turbine operation status, wind turbine blade angle value, wind turbine generator speed, wind turbine power limit, etc. as the basis for data cleaning. Instead, the abnormal data can be cleaned by relying on real-time wind speed and real-time active power to accurately fit the power curve.

[0069] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0071] Figure 1 is a flow chart of a wind turbine power curve fitting method according to an embodiment of the present invention;

[0072] Figure 2 is a power curve diagram of the F01 unit in the first wind farm using different algorithms according to an embodiment of the present invention;

[0073] Figure 3 is a power curve diagram of the F02 unit in the first wind farm using different algorithms according to an embodiment of the present invention;

[0074] Figure 4 is a power curve diagram of the F03 unit in the first wind farm using different algorithms according to an embodiment of the present invention;

[0075] Figure 5 is a power curve diagram of the F04 unit in the first wind farm using different algorithms according to an embodiment of the present invention;

[0076] Figure 6 is a power curve diagram of the F01 unit in the second wind farm using different algorithms according to an embodiment of the present invention;

[0077] Figure 7 is a power curve diagram of the F02 unit in the second wind farm using different algorithms according to an embodiment of the present invention;

[0078] Figure 8 is a power curve diagram of the F03 unit in the second wind farm using different algorithms according to an embodiment of the present invention;

[0079] Fig. 9 is a power curve diagram of the F04 unit in the second wind farm using different algorithms according to an embodiment of the present invention;

[0080] Fig.10 4 is a block diagram of a wind turbine power curve fitting device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0081] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0082] The wind turbine power curve fitting method, device and electronic device according to the embodiments of the present invention are described below with reference to the accompanying drawings.

[0083] Figure 1 is a flow chart of a wind turbine power curve fitting method according to an embodiment of the present invention.

[0084] like Figure 1 As shown, the wind turbine power curve fitting method according to the embodiment of the present invention comprises the following steps:

[0085] S1, obtaining the operation data of the wind turbine generator set within a set time period; wherein the operation data includes real-time wind speed and real-time active power.

[0086] In the embodiment of the present invention, the set duration can be 10 minutes. The real-time wind speed of the wind turbine is obtained by installing wind speed sensors on the wind turbine. These wind speed sensors can monitor the wind speed at the location of the wind turbine in real time, and convert the measured wind speed data into the real value of the incoming wind speed in front of the impeller according to the correction model such as the cabin transfer function. The corrected real-time wind speed data are immediately recorded in the data acquisition system of the wind turbine or the remote monitoring center for subsequent analysis and management; the real-time active power of the wind turbine is obtained by measuring the power output of the wind turbine, which usually involves monitoring and calculating the current and voltage output by the generator of the wind turbine. The real-time active power data can directly reflect the power generation capacity of the wind turbine and the relationship between it and factors such as wind speed.

[0087] S2, taking the real-time wind speed as a reference object and combining the cut-in wind speed value of the wind turbine, divides the real-time wind speed data into multiple wind speed intervals according to the set wind speed partition step.

[0088] That is to say, the lower limit wind speed of the first wind speed interval among the multiple wind speed intervals is 0, and the upper limit wind speed value is less than the cut-in wind speed value, specifically the cut-in wind speed value minus half of the set wind speed partition step; the lower limit wind speed value of the second wind speed interval among the multiple wind speed intervals is the cut-in wind speed value minus half of the wind speed partition step, and the upper limit wind speed value is the cut-in wind speed value plus half of the set wind speed partition step, that is, the median of the second wind speed interval is the cut-in wind speed value; and so on, it can be known that the median of the i-th (i is a positive integer greater than or equal to 2) wind speed interval is the cut-in wind speed value plus i-2 partition step values. That is to say, the lower limit wind speed value of the i-th wind speed interval among the multiple wind speed intervals is the upper limit wind speed value of the i-1th wind speed interval, and the upper limit wind speed value of the i-th wind speed interval is the upper limit wind speed value of the i-1th wind speed interval plus the set wind speed partition step.

[0089] Theoretically, the real-time active power is proportional to the cube of the real-time wind speed. The real-time wind speed is divided into wind speed partitions according to the set wind speed partition step size, such as 0.5m / s. In theory, the real-time active power corresponding to the partition with high wind speed should be higher than the real-time active power corresponding to the partition with low wind speed. At the same time, its maximum power value should be controlled by the cube ratio of the wind speed upper limit value. The ratio of the cube of the upper limit wind speed of interval i to the cube of the upper limit wind speed of its adjacent low wind speed interval is defined as P. i , i.e. the fifth value described in the present invention, then:

[0090]

[0091] Table 1 below shows the theoretical P values ​​for each wind speed range for a wind turbine with a cut-in wind speed of 2.5 m / s and a rated wind speed of 9.5 m / s. i value.

[0092] Table 1

[0093]

[0094] S3, determining the lower limit power value and the upper limit power value of each wind speed interval.

[0095] After the wind speed zones are divided, determining the lower limit power value and the upper limit power value of the first wind speed interval includes: determining that the lower limit power value of the first wind speed interval is greater than 0; determining that the upper limit power value of the first wind speed interval is the theoretical active power corresponding to the cut-in wind speed value.

[0096] Due to different designs of wind turbines, the power corresponding to the cut-in wind speed value of some units is lower. At this time, it is necessary to calculate the ratio of the theoretical active power corresponding to the median wind speed value of the third wind speed interval to the theoretical active power corresponding to the cut-in wind speed value as the first value, and calculate the cube of the ratio of the median wind speed value of the third wind speed interval to the cut-in wind speed value as the second value. When the difference between the first value and the second value is greater than the set difference, the upper limit power value of the first wind speed interval is updated to the theoretical active power corresponding to the median wind speed value of the third wind speed interval.

[0097] In an embodiment of the present invention, the lower limit power value and the upper limit power value of the i-th wind speed interval are determined, wherein i is an integer greater than or equal to 2, including: sorting the effective active powers in the effective active power data set corresponding to the i-1-th wind speed interval from large to small, and obtaining the effective active power value arranged at the first set percentage position as the lower limit power value of the i-th wind speed interval; determining the upper limit power value of the i-th wind speed interval according to the maximum effective active power in the effective active power data set corresponding to the i-1-th wind speed interval, the upper limit wind speed value of the i-1-th wind speed interval, the upper limit wind speed value of the i-th wind speed interval and the second set percentage.

[0098] According to the maximum effective active power in the effective active power data set corresponding to the i-1th wind speed interval, the upper limit wind speed value of the i-1th wind speed interval, the upper limit wind speed value of the i-th wind speed interval and the second set percentage, the upper limit power value of the i-th wind speed interval is determined, including: calculating the cube of the upper limit wind speed value of the i-1th wind speed interval as the third value; calculating the cube of the upper limit wind speed value of the i-th wind speed interval as the fourth value; taking the ratio of the fourth value to the third value as the fifth value (when the median wind speed of the i-th wind speed partition is greater than the rated wind speed of the wind turbine generator set, the fifth value is 1); taking the product of the maximum effective active power in the effective active power data set corresponding to the i-1th wind speed interval, the fifth value and the second set percentage as the upper limit power value of the i-th wind speed interval.

[0099] As shown in Table 1 above, the Pi value of the third interval (i.e., interval 03) is 1.65, then the maximum power of interval 03 should be within 1.65 times the maximum power of the second interval (interval 02), and a power value greater than 1.65 times can be considered an abnormal point. However, in actual operation, the upper limit wind speed of some wind speed partitions may not have a corresponding power value, especially when the number of data samples is small, the upper limit wind speed of the partition may be missing, resulting in the maximum power displayed by the partition is not the true maximum power. For this reason, the Pi value needs to have a certain redundancy, so the Pi value of all partitions is provided with a second set percentage such as 20% redundancy, that is, multiplied by 1.2 times. Obviously, the upper limit power value of a certain wind speed partition can be calculated from the maximum power value of its adjacent high wind speed partition.

[0100] S4, according to the lower limit power value and the upper limit power value of each wind speed interval, the abnormal real-time active power in the corresponding wind speed interval is eliminated, and a corresponding effective active power data set is generated.

[0101] After calculating the lower limit power value and the upper limit power value of each wind speed interval, the present invention can eliminate the real-time active power that does not fall between the lower limit power value and the upper limit power value, that is, kick out the abnormal real-time active power, thereby obtaining valid data of the real-time active power, and generating an effective active power data set corresponding to each wind speed interval.

[0102] S5, fitting a power curve of the wind turbine generator set according to all real-time wind speed data in each wind speed interval and an effective active power data set corresponding to each wind speed interval.

[0103] The execution process of step S5 is as follows: obtaining the average wind speed of all real-time wind speed data in each wind speed interval, and obtaining the average power of the effective active power data set corresponding to each wind speed interval, and fitting the power curve of the wind turbine according to the average wind speed and average power in each wind speed interval.

[0104] Therefore, the wind turbine power curve fitting method of the present invention does not need the wind turbine operation data report within a set time period to provide additional parameters such as the wind turbine operation status, wind turbine blade angle value, wind turbine generator speed, wind turbine power limit, etc. as the basis for data cleaning, but instead relies on real-time wind speed and real-time active power for processing to accurately fit the power curve.

[0105] The following describes the process of implementing the wind turbine power curve fitting method of the present invention in combination with specific data as follows:

[0106] First, obtain the operation data of the wind turbines within 10 minutes, including the real-time wind speed and real-time active power. Then, take the real-time wind speed as the reference object, divide the wind speed into zones with a step size of 0.5 m / s, and sort them from small to large according to the median wind speed of the wind speed zones. For example, for a wind turbine with a cut-in wind speed value of 2.5 m / s, its wind speed zones can be defined as interval 01 (0, 2.25], interval 02 (2.25, 2.75], interval 03 (2.75, 3.25], interval 04 (3.25, 3.75], interval 05 (3.75, 4.25], interval 06 (4.25, 4.75], ...

[0107] Then, the values ​​of the second percentage (UPercent) and the first percentage (DPercent) are set to 120% and 10% respectively. The second percentage (UPercent) provides a maximum value redundancy for the power interval, which is a redundancy coefficient, and the first percentage (DPercent) determines the minimum value of the power interval.

[0108] Among them, the real-time wind speed corresponding to interval 01 is generally lower than the cut-in wind speed value. Invalid data with real-time active power less than or equal to 0 and data with real-time active power greater than the cut-in wind speed value are eliminated in this wind speed interval, that is, the lower limit power value of interval 01 is greater than 0, and the upper limit power value is the theoretical power corresponding to the cut-in wind speed value. However, due to different designs of wind turbines, the power corresponding to the cut-in wind speed value of some units is relatively low, and its ratio to the power corresponding to the adjacent high wind speed greatly exceeds the theoretical difference. At this time, the power corresponding to the adjacent high wind speed of the cut-in wind speed value can be selected as the upper limit power value of interval 01. The cleaned active power of interval 01 is sorted from large to small to form an effective active power data set, and the 10% (DPercent) percentile of the effective active power data set is taken and set as A1. In addition, let A2 be M times the maximum value in the effective active power data set, and M=UPercent*Pi, Pi is the ratio of the upper limit wind speed cube of the adjacent high wind speed interval i, that is, calculate the cube of the upper limit wind speed value of the i-1th wind speed interval as the third value, and the cube of the upper limit wind speed value of the i-th wind speed interval as the fourth value, and take the ratio of the fourth value to the third value as the fifth value Pi. Among them, A1 and A2 are the lower limit power value and the upper limit power value of the adjacent high wind speed interval.

[0109] After that, the real-time active power of interval 02 is screened, and the power-limited operation data less than A1 and the random discrete points greater than A2 are eliminated. Similarly, the effective active power data of interval 02 after screening is sorted from large to small, and its 10% (DPercent) percentage position value and M times the maximum value are calculated, and they are used as the screening basis for the effective active power data of interval 03, that is, the lower limit power value and the upper limit power value.

[0110] And so on, until all wind speed zones are processed. It is worth mentioning again that when the median wind speed of the wind speed interval is greater than the rated wind speed of the wind turbine, Pi = 1.

[0111] Finally, the average wind speed of all real-time wind speed data in each wind speed interval and the average active power of the effective active power data set corresponding to each wind speed interval are obtained, and a scatter plot of the average wind speed and average active power after processing is drawn, and compared with the original scatter plot to view the effect of elimination. It should be noted that the UPercent and DPercent values ​​can be fine-tuned according to actual conditions (no adjustment is required in most cases). According to the final processed data, the data other than the cut-in wind speed value and the cut-out wind speed are eliminated, the average wind speed and average active power of each wind speed partition are calculated, and a power curve is drawn.

[0112] Specific implementation case 1:

[0113] In order to verify the effectiveness of the wind turbine power curve fitting method (hereinafter referred to as percentile recursive method) of the present invention, the power curve is fitted by the percentile recursive method of the present invention according to the operating data of the four wind turbines in the first wind farm within 10 minutes, and compared with the Bin value method of IEC. The results are shown in Table 2 below, where "uncleaned" means that the 10-minute operating data has not been cleaned in any form and is directly processed by the Bin value method, that is, all real-time active powers of each wind speed partition are directly averaged; "parameter screening" means that the 10-minute data is pre-processed to eliminate the data in the power limit state, the data with wind turbine power less than or equal to 0, and the data with blade angle greater than 20-degree data, and then the remaining valid data is processed by the Bin value method, which is a commonly used power curve fitting method, and it can be regarded as the actual power curve; "percentile recursion" refers to the method described in the present invention, and the four units are set with the same second percentage UPercent (specific value is 120%) and the first percentage DPercent (specific value is 10%) to process the 10-minute data. The method of the present invention does not need to use additional parameters such as blade angle and wind turbine operating status to eliminate abnormal data in the 10-minute data in advance, but uses the physical relationship that power is proportional to the cube of wind speed, and adopts a recursive form to eliminate abnormal data. The method of the present invention is particularly suitable for computer programming, and is particularly suitable for scenarios where parameters such as blade angle and wind turbine operating status cannot be provided in the 10-minute data.

[0114] Table 2

[0115]

[0116] By analyzing the power data of "parameter screening" and "percentile recursion" of each unit, it can be found that they have a very high linear relationship. The linear fitting functions between the power data calculated by "percentile recursion" and "parameter screening" of the four units are:

[0117] Y=1.0012X-6.301(F01)

[0118] Y=0.9984X-1.7687(F02)

[0119] Y=0.999X-0.9574(F03)

[0120] Y=0.9993X-1.4168(F04)

[0121] Among them, X represents "parameter screening", that is, the Bin value result after screening, and Y represents the result of the "percentile recursive algorithm" described in the present invention.

[0122] Figure 2-Figure 5Three algorithms are used to draw the power curve of each unit. Method 1 is the Bin value method after parameter screening (taken as the real actual operating power curve), method 2 is the commonly used maximum probability density method (without cleaning the data in advance), and method 3 is the "percentile recursive algorithm" of the present invention. It can be seen that the method of the present invention is very close to the actual operating power curve, and the method of the present invention can effectively remove abnormal data such as power limit scatter points.

[0123] Specific implementation case 2:

[0124] The 10-minute data of the four wind turbines in the second wind farm that have been connected to the grid for three months are fitted with the "percentile recursive algorithm" described in the present invention. The second percentage UPercent and the first percentage DPercent are still 120% and 10% respectively. Similarly, the fitting results are also compared with the Bin value method of IEC. The results are shown in Table 3 below. Similar to the above-mentioned specific implementation case 1, the "percentile recursive algorithm" of the present invention is still highly consistent with the Bin value method of IEC. The linear fitting functions between them are:

[0125] Y=1.0088X+13.8631(A01 unit)

[0126] Y=1.0129X+0.3421(A02 unit)

[0127] Y=1.0107X+10.2987(A03 unit)

[0128] Y=1.0087X+4.7777(A04 unit)

[0129] Wherein, X represents the Bin value result after screening, and Y is the result of the “percentile recursive algorithm” described in the present invention.

[0130] Table 3

[0131]

[0132] Similarly, three algorithms are used to draw the power curves of the four units respectively, such as Figure 6-Figure 9 As shown, it can be seen that the "percentile recursive method" of the present invention still maintains a high degree of consistency with the actual operating power curve, which once again proves that the algorithm can effectively remove abnormal data such as power limit scatter points.

[0133] Therefore, the present invention utilizes the physical law that wind power is proportional to the cube of wind speed, and introduces the ideas of recursion and percentile, and uses the power of low wind speed partitions to design the power threshold of adjacent high wind speed partitions, thereby eliminating abnormal data of adjacent high wind speed partitions, thereby achieving the effect of not relying on wind turbine state parameters, blade angle parameters, generator speed and other parameters, and effectively eliminating abnormal data such as limited power operation, which is particularly suitable for scenarios where such parameters cannot be provided in 10-minute data for data cleaning. The method of the present invention is simple in design, has strong program feasibility, fast calculation speed, and accurate fitting results.

[0134] In summary, according to the wind turbine power curve fitting method of the embodiment of the present invention, the operation data of the wind turbine including the real-time wind speed and the real-time active power within the set time length are first obtained, and the real-time wind speed is used as a reference object, combined with the cut-in wind speed value of the wind turbine, and the real-time wind speed data is divided into multiple wind speed intervals according to the set wind speed partition step, and then the lower limit power value and the upper limit power value of each wind speed interval are determined, and according to the lower limit power value and the upper limit power value of each wind speed interval, the abnormal real-time active power in the corresponding wind speed interval is eliminated, and an effective active power data set is generated, and finally, according to all the real-time wind speed data in each wind speed interval and the effective active power data set corresponding to each wind speed interval, the power curve of the wind turbine is fitted. Therefore, the method does not require the operation data report of the wind turbine within the set time length to provide additional parameters such as the wind turbine operation status, the wind turbine blade angle value, the wind turbine generator speed, and the wind turbine power limit as the basis for data cleaning, and the cleaning of abnormal data can be completed by relying on the real-time wind speed and the real-time active power, so as to accurately fit the power curve.

[0135] Fig.10 4 is a block diagram of a wind turbine power curve fitting device according to an embodiment of the present invention.

[0136] like Fig.10 As shown, the wind turbine power curve fitting device 100 according to the embodiment of the present invention includes: an acquisition module 110 , a division module 120 , a determination module 130 , a removal module 140 and a fitting module 150 .

[0137] Among them, the acquisition module 110 is used to obtain the operating data of the wind turbine within a set time period; wherein the operating data includes real-time wind speed and real-time active power. The division module 120 is used to use the real-time wind speed as a reference object, combined with the cut-in wind speed value of the wind turbine, and divide the real-time wind speed data into multiple wind speed intervals according to the set wind speed partition step. The determination module 130 is used to determine the lower limit power value and the upper limit power value of each wind speed interval. The elimination module 140 is used to eliminate the abnormal real-time active power in the corresponding wind speed interval according to the lower limit power value and the upper limit power value of each wind speed interval, and generate an effective active power data set. The fitting module 150 is used to fit the power curve of the wind turbine according to each wind speed interval and the effective active power data set corresponding to each wind speed interval.

[0138] According to an embodiment of the present invention, the division module 120 is used to divide the real-time wind speed data into multiple wind speed intervals according to the set wind speed partition step size, taking the real-time wind speed as a reference object and combining the cut-in wind speed value of the wind turbine generator set, including:

[0139] The lower limit wind speed value of the first wind speed interval among the multiple wind speed intervals is 0, and the upper limit wind speed value of the first wind speed interval is the cut-in wind speed value minus half of the set wind speed partition step;

[0140] The lower limit wind speed value of the i-th wind speed interval among multiple wind speed intervals is the upper limit wind speed value of the i-1-th wind speed interval, and the upper limit wind speed value of the i-th wind speed interval is the upper limit wind speed value of the i-1-th wind speed interval plus the set wind speed partition step; wherein i is a positive integer greater than or equal to 2.

[0141] According to an embodiment of the present invention, when the determination module 130 is used to determine the lower limit power value and the upper limit power value of the first wind speed interval, it includes:

[0142] Determine that the lower limit power value of the first wind speed interval is greater than 0;

[0143] The upper limit power value of the first wind speed interval is determined to be the theoretical active power corresponding to the cut-in wind speed value.

[0144] According to one embodiment of the present invention, the above device further includes:

[0145] An updating module is used to calculate the ratio of the theoretical active power corresponding to the median wind speed value of the third wind speed interval to the theoretical active power corresponding to the cut-in wind speed value as the first value, and calculate the cube of the ratio of the median wind speed value of the third wind speed interval to the cut-in wind speed value as the second value, and when the difference between the first value and the second value is greater than the set difference, update the upper limit power value of the first wind speed interval to the theoretical active power corresponding to the median wind speed value of the third wind speed interval.

[0146] According to an embodiment of the present invention, when the determination module 130 is used to determine the lower limit power value and the upper limit power value of the i-th wind speed interval, it includes:

[0147] Sort the effective active powers in the effective active power data set corresponding to the i-1th wind speed interval from large to small, and obtain the effective active power value arranged at the first set percentage position as the lower limit power value of the i-th wind speed interval;

[0148] The upper limit power value of the i-th wind speed interval is determined according to the maximum effective active power in the effective active power data set corresponding to the i-1-th wind speed interval, the upper limit wind speed value of the i-1-th wind speed interval, the upper limit wind speed value of the i-th wind speed interval and the second set percentage.

[0149] According to one embodiment of the present invention, the determination module 130 is used to determine the upper limit power value of the i-th wind speed interval according to the maximum effective active power in the effective active power data set corresponding to the i-1th wind speed interval, the upper limit wind speed value of the i-1th wind speed interval, the upper limit wind speed value of the i-th wind speed interval and the second set percentage, including:

[0150] Calculate the cube of the upper limit wind speed value of the i-1th wind speed interval as the third value;

[0151] Calculate the cube of the upper limit wind speed value of the i-th wind speed interval as the fourth value;

[0152] The ratio of the fourth value to the third value is taken as the fifth value;

[0153] The product of the maximum effective active power in the effective active power data set corresponding to the i-1th wind speed interval, the fifth value and the second set percentage is used as the upper limit power value of the i-th wind speed interval.

[0154] According to an embodiment of the present invention, when the median wind speed value in the i-th wind speed interval is greater than the rated wind speed of the wind turbine generator set, the fifth value is 1.

[0155] According to an embodiment of the present invention, the fitting module 150 is used to fit the power curve of the wind turbine according to all real-time wind speed data in each wind speed interval and the effective active power data set corresponding to each wind speed interval, including:

[0156] Get the average wind speed of all real-time wind speed data in each wind speed interval;

[0157] Obtain the average power of the effective active power data set corresponding to each wind speed interval;

[0158] According to the average wind speed and average power in each wind speed interval, the power curve of the wind turbine is fitted.

[0159] It should be noted that for details not disclosed in the wind turbine power curve fitting device of the embodiment of the present invention, please refer to the details disclosed in the wind turbine power curve fitting method of the embodiment of the present invention, and no further details will be given here.

[0160] According to the wind turbine power curve fitting device of the embodiment of the present invention, the operation data of the wind turbine within the set time length is obtained by the acquisition module, and the operation data includes real-time wind speed and real-time active power. The real-time wind speed data is divided into multiple wind speed intervals according to the set wind speed partition step length by the division module with the real-time wind speed as the reference object and the cut-in wind speed value of the wind turbine. The lower limit power value and the upper limit power value of each wind speed interval are determined by the determination module. The abnormal real-time active power in the corresponding wind speed interval is eliminated according to the lower limit power value and the upper limit power value of each wind speed interval by the elimination module, and an effective active power data set is generated. The power curve of the wind turbine is fitted by the fitting module according to each wind speed interval and the effective active power data set corresponding to each wind speed interval. Therefore, the device does not need the operation data report of the wind turbine within the set time length to provide additional parameters such as the wind turbine operation status, the wind turbine blade angle value, the wind turbine generator speed, and the wind turbine power limit as the basis for data cleaning. The cleaning of abnormal data can be completed by relying on the real-time wind speed and the real-time active power, so as to accurately fit the power curve.

[0161] Based on the above embodiments, the present invention further provides an electronic device.

[0162] An electronic device according to an embodiment of the present invention comprises: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned wind turbine power curve fitting method.

[0163] The electronic device of the embodiment of the present invention executes the above-mentioned wind turbine power curve fitting method, so that there is no need for the wind turbine operation data report within a set time period to provide additional parameters such as the wind turbine operation status, wind turbine blade angle value, wind turbine generator speed, wind turbine power limit, etc. as the basis for data cleaning. Instead, the cleaning of abnormal data can be completed by relying on real-time wind speed and real-time active power to accurately fit the power curve.

[0164] Based on the above embodiments, the present invention also proposes a computer-readable storage medium.

[0165] The computer instructions in the computer-readable storage medium of the embodiment of the present invention are used to enable a computer to execute the above-mentioned wind turbine power curve fitting method.

[0166] The computer-readable storage medium of an embodiment of the present invention executes the above-mentioned wind turbine power curve fitting method, so that there is no need for the wind turbine operation data report within a set time period to provide additional parameters such as the wind turbine operation status, wind turbine blade angle value, wind turbine generator speed, wind turbine power limit, etc. as the basis for data cleaning. Instead, the cleaning of abnormal data can be completed by relying on real-time wind speed and real-time active power to accurately fit the power curve.

[0167] Based on the above embodiments, the present invention also proposes a computer program product.

[0168] In an embodiment of the present invention, when the instruction processor in the computer program product is executed, the above-mentioned wind turbine power curve fitting method is executed.

[0169] The computer program product of the embodiment of the present invention executes the above-mentioned wind turbine power curve fitting method, so that there is no need for the wind turbine operation data report within a set time period to provide additional parameters such as the wind turbine operation status, wind turbine blade angle value, wind turbine generator speed, wind turbine power limit, etc. as the basis for data cleaning. Instead, the abnormal data can be cleaned by relying on real-time wind speed and real-time active power to accurately fit the power curve.

[0170] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0171] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0172] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0173] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0174] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0175] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0176] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0177] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A wind turbine power curve fitting method, characterized in that: include: Obtaining the operating data of the wind turbine generator set within a set time period; wherein the operating data includes real-time wind speed and real-time active power; Taking the real-time wind speed as a reference object and combining the cut-in wind speed value of the wind turbine generator set, the real-time wind speed data is divided into a plurality of wind speed intervals according to a set wind speed partition step, the lower limit wind speed value of the first wind speed interval among the plurality of wind speed intervals is 0, the upper limit wind speed value of the first wind speed interval is the cut-in wind speed value minus one-half of the set wind speed partition step, the lower limit wind speed value of the i-th wind speed interval among the plurality of wind speed intervals is the upper limit wind speed value of the i-1th wind speed interval, and the upper limit wind speed value of the i-th wind speed interval is the upper limit wind speed value of the i-1th wind speed interval plus the set wind speed partition step; wherein, i is a positive integer greater than or equal to 2; Determining a lower power limit value and an upper power limit value for each of the wind speed intervals; According to the lower limit power value and the upper limit power value of each wind speed interval, the abnormal real-time active power in the corresponding wind speed interval is eliminated, and an effective active power data set is generated; The power curve of the wind turbine generator set is obtained by fitting according to all the real-time wind speed data in each of the wind speed intervals and the effective active power data set corresponding to each of the wind speed intervals.

2. The method according to claim 1, characterized in that Determine the lower power limit and upper power limit of the first wind speed interval, including: Determine that the lower limit power value of the first wind speed interval is greater than 0; An upper limit power value of the first wind speed interval is determined to be the theoretical active power corresponding to the cut-in wind speed value.

3. The method according to claim 2, characterized in that The method further comprises: Calculate the ratio of the theoretical active power corresponding to the median wind speed value of the third wind speed interval to the theoretical active power corresponding to the cut-in wind speed value as the first value; Calculate the cube of the ratio of the median wind speed value of the third wind speed interval to the cut-in wind speed value as the second value; If the difference between the first value and the second value is greater than a set difference, the upper limit power value of the first wind speed interval is updated to the theoretical active power corresponding to the median wind speed value of the third wind speed interval.

4. The method according to claim 1, characterized in that Determine the lower power limit and upper power limit of the i-th wind speed interval, including: Sort the effective active powers in the effective active power data set corresponding to the i-1th wind speed interval from large to small, and obtain the effective active power value arranged at the first set percentage position as the lower limit power value of the i-th wind speed interval; The upper limit power value of the i-th wind speed interval is determined according to the maximum effective active power in the effective active power data set corresponding to the i-1-th wind speed interval, the upper limit wind speed value of the i-1-th wind speed interval, the upper limit wind speed value of the i-th wind speed interval and the second set percentage.

5. The method according to claim 4, characterized in that The method of determining the upper limit power value of the i-th wind speed interval according to the maximum effective active power in the effective active power data set corresponding to the i-1-th wind speed interval, the upper limit wind speed value of the i-1-th wind speed interval, the upper limit wind speed value of the i-th wind speed interval, and the second set percentage includes: Calculate the cube of the upper limit wind speed value of the (i-1)th wind speed interval as the third value; Calculate the cube of the upper limit wind speed value of the i-th wind speed interval as the fourth value; The ratio of the fourth value to the third value is used as the fifth value; The product of the maximum effective active power in the effective active power data set corresponding to the i-1th wind speed interval, the fifth value and the second set percentage is used as the upper limit power value of the i-th wind speed interval.

6. The method according to claim 5, characterized in that When the median wind speed value of the i-th wind speed interval is greater than the rated wind speed of the wind turbine generator set, the fifth value is 1.

7. The method according to claim 1, characterized in that The step of fitting the power curve of the wind turbine generator set according to all the real-time wind speed data in each of the wind speed intervals and the effective active power data set corresponding to each of the wind speed intervals comprises: Get the average wind speed of all real-time wind speed data in each wind speed interval; Obtain the average power of the effective active power data set corresponding to each wind speed interval; The power curve of the wind turbine generator set is obtained by fitting according to the average wind speed and the average power in each wind speed interval.

8. A wind turbine power curve fitting device, characterized in that: include: An acquisition module is used to acquire the operation data of the wind turbine generator set within a set time period; wherein the operation data includes real-time wind speed and real-time active power; A partitioning module, for taking the real-time wind speed as a reference object, combining the cut-in wind speed value of the wind turbine generator set, and dividing the real-time wind speed data into a plurality of wind speed intervals according to a set wind speed partitioning step, wherein the lower limit wind speed value of the first wind speed interval among the plurality of wind speed intervals is 0, the upper limit wind speed value of the first wind speed interval is the cut-in wind speed value minus one-half of the set wind speed partitioning step, the lower limit wind speed value of the i-th wind speed interval among the plurality of wind speed intervals is the upper limit wind speed value of the i-1th wind speed interval, and the upper limit wind speed value of the i-th wind speed interval is the upper limit wind speed value of the i-1th wind speed interval plus the set wind speed partitioning step; wherein i is a positive integer greater than or equal to 2; A determination module, used to determine a lower limit power value and an upper limit power value of each wind speed interval; A removal module, used to remove abnormal real-time active power in the corresponding wind speed interval according to the lower limit power value and the upper limit power value of each wind speed interval, and generate an effective active power data set; The fitting module is used to fit the power curve of the wind turbine according to each of the wind speed intervals and the effective active power data set corresponding to each of the wind speed intervals.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the wind turbine power curve fitting method according to any one of claims 1 to 7.

Images