Numerical calculation method for rotating speed parameters of generator of wind turbine generator

Abstract

The invention discloses a numerical calculation method for rotating speed parameters of a generator of a wind turbine generator, which belongs to the technical field of wind power plant data processing, and comprises the following steps: acquiring operation data of the wind turbine generator; wherein the operation data of the wind turbine generator comprises active power data and generator rotating speed data; based on the operation data, the rated rotating speed of the wind driven generator is calculated; calculating the grid-connected rotating speed of the wind driven generator based on the operation data; based on the operation data, rotating speed curve fitting is carried out, and a rotating speed curve is obtained; wherein the rotating speed curve is used for judging whether the rotating speed of the generator is matched with the output power so as to judge whether the generator is normal. By adopting the technical scheme, the SCADA data of the wind turbine generator can be efficiently utilized to carry out numerical calculation on parameters such as the grid-connected rotating speed and the rated rotating speed of the generator of the wind turbine generator, and the problems that a visual inspection method is not accurate enough and cannot be automated are practically solved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind farm data processing, and particularly to a numerical calculation method for the generator speed parameters of a wind turbine. Background Art

[0002] With the continuous progress of technology and the gradual reduction of production costs, wind power generation has become an important part of the new energy scale growth. As the core component of a wind turbine, the performance and operating health of the generator are directly related to the power generation efficiency and power supply quality of the entire unit. Generally, in the technical agreement for equipment procurement of a wind turbine, the wind turbine manufacturer will provide the main parameters of the wind generator, such as rated power, rated voltage, rated speed, grid connection speed, power factor, etc. Calculating and comparing the actual rated speed and grid connection speed of a wind generator is an important part of detecting whether the wind generator meets the technical requirements.

[0003] However, in actual work, we found that the actual rated speed and grid connection speed of the wind generators in some wind farms do not match the agreements in the technical agreement, and there are situations such as under - equipped with high - use or over - equipped with low - use. However, due to the lack of methods for analyzing and numerically calculating the grid connection speed and rated speed of wind generators by operation and maintenance personnel such as the owners, such problems have not been discovered. Therefore, there is an urgent need for a calculation method that can calculate parameters such as the grid connection speed and rated speed of a wind generator based on the actual operation data of the wind turbine unit, and determine whether the speed of the wind generator matches the corresponding power and whether there are abnormalities.

[0004] In the prior art, the grid connection speed and rated speed of a wind turbine are obtained by plotting a scatter diagram of power - generator speed, and then estimating the grid connection speed and rated speed of the wind generator by visually observing the data concentration area of the scatter diagram by hand. Although this method is intuitive, it lacks intelligence and accuracy, is easily affected by human factors, and is not conducive to batch calculation of multiple units in an entire wind farm. Summary of the Invention

[0005] The present invention provides a numerical calculation method for the generator speed parameters of a wind turbine unit to solve the technical problems that the existing methods for determining the grid connection speed and rated speed of a wind turbine are intuitive, but lack intelligence and accuracy, are easily affected by human factors, and are not conducive to batch calculation of multiple units in an entire wind farm.

[0006] To solve the above - mentioned technical problems, the present invention provides the following technical solutions:

[0007] On the one hand, the present invention provides a numerical calculation method for the generator speed parameters of a wind turbine unit, including:

[0008] Acquire the operation data of the wind turbine generator set; wherein the operation data of the wind turbine generator set includes: active power data of the wind turbine generator set and generator speed data of the wind turbine generator set;

[0009] Based on the operating data, calculating the rated speed of the wind turbine;

[0010] Based on the operating data, calculating the grid-connected speed of the wind turbine generator;

[0011] Based on the operating data, a speed curve is fitted to obtain a speed curve; wherein the speed curve is used to determine whether the speed of the generator matches the output power, and further determine whether the generator is normal.

[0012] Further, based on the operating data, the rated speed of the wind turbine is calculated, including:

[0013] Based on the operating data, a rated speed value R1 is obtained from the power dimension;

[0014] Based on the operating data, a rated speed value R2 is obtained from the speed dimension;

[0015] The maximum value of R1 and R2 is taken as the rated speed of the wind turbine.

[0016] Furthermore, based on the operating data, a rated speed value R1 is obtained from the power dimension, including:

[0017] Extracting active power data and generator speed data with a time resolution of T minutes from the operating data, aligning the extracted active power data and generator speed data in the time dimension, and using the aligned active power data and generator speed data to form a first data set; removing active power data not greater than 0 and its corresponding motor speed data from the first data set to obtain a second data set; wherein T is a preset value;

[0018] Filter out the active power data and the corresponding generator speed data that are greater than the first preset power threshold in the second data set, and divide the filtered data into N intervals according to the size of the active power, and for each divided interval, obtain the maximum generator speed value therein; wherein N is a preset value;

[0019] The calculated maximum generator speed values ​​of each interval are re-arranged in ascending order, and the sorted maximum generator speed values ​​of each interval form a third data set;

[0020] Eliminate the first n and last n values ​​in the third data set to obtain a fourth data set, wherein n is a preset value;

[0021] Take the average value of the data in the fourth dataset as the rated speed value R1 obtained from the power dimension.

[0022] Further, based on the operating data, obtain a rated speed value R2 from the speed dimension, including:

[0023] Equally partition the filtered generator speed data to obtain multiple speed partitions; wherein, when equally partitioning the filtered generator speed data, the number M of speed partitions needs to satisfy 10 ≤ M ≤ 300;

[0024] For each speed partition, calculate the ratio of the amount of data therein to the total amount of generator speed data;

[0025] Eliminate the speed partitions with ratios less than the preset ratio threshold; for the remaining speed partitions, use the kernel density estimation algorithm to calculate the maximum probability speed of each speed interval;

[0026] Take the maximum value among all the maximum probability speeds as the rated speed value R2 obtained from the speed dimension.

[0027] Further, based on the operating data, calculate the grid connection speed of the wind turbine, including:

[0028] Based on the operating data, obtain a grid connection speed value R3 from the power dimension;

[0029] Based on the operating data, also obtain a grid connection speed value R4 from the speed probability dimension;

[0030] Take the minimum value of R3 and R4 as the grid connection speed of the wind turbine.

[0031] Further, based on the operating data, obtain a grid connection speed value R3 from the power dimension, including:

[0032] Extract the active power data and generator speed data with a time resolution of T minutes from the operating data, align the extracted active power data and generator speed data in the time dimension, and use the aligned active power data and generator speed data to form a fifth dataset; eliminate the active power data not greater than 0 and its corresponding motor speed data in the fifth dataset to obtain a sixth dataset; wherein, T is a preset value;

[0033] Filter out the active power data less than the second preset power threshold and its corresponding generator speed data in the sixth dataset, and equally divide the filtered data into N intervals according to the magnitude of the active power. For each divided interval, obtain the maximum generator speed value therein; wherein, N is a preset value;

[0034] Re - sort the calculated maximum generator speed values of each interval in ascending order, and form the seventh data set with the maximum generator speed values of each interval after sorting;

[0035] Eliminate the first n values and the last n values in the seventh data set to obtain the eighth data set; where n is a preset value;

[0036] Take the average value of the data in the eighth data set as the grid - connected speed value R3 obtained from the power dimension.

[0037] Furthermore, based on the operation data, a grid - connected speed value R4 is also obtained from the speed probability dimension, including:

[0038] Equal - partition the selected generator speed data to obtain multiple speed partitions; when equal - partitioning the selected generator speed data, the number M of speed partitions needs to satisfy 10 ≤ M ≤ 300;

[0039] For each speed partition, calculate the ratio of the data volume in it to the total generator speed data volume, and use the kernel density estimation algorithm to calculate the maximum probability speed and the maximum probability active power of each speed interval;

[0040] Re - sort the speed partitions in descending order according to the ratio;

[0041] Select the first partition K that meets the following conditions from the sorted speed partitions t :

[0042] (1) The maximum probability speed of the speed partition is less than 0.75 * MR;

[0043] (2) The maximum probability active power of the speed partition is less than 0.2 * MP;

[0044] Where MP represents the maximum active power data in the sixth data set; MR represents the maximum generator speed data in the sixth data set;

[0045] Take the maximum probability speed of K t as the grid - connected speed value R4 obtained from the speed probability dimension.

[0046] Furthermore, based on the operation data, perform speed curve fitting to obtain a speed curve, including:

[0047] Extract the active power data and generator speed data with a time resolution of T minutes in the operation data, align the active power data and the generator speed data in the time dimension, and then eliminate the active power data not greater than 0 and its corresponding motor speed data to obtain the ninth data set; where T is a preset value;

[0048] Equal - partition the active power data in the ninth dataset to obtain multiple power partitions;

[0049] For each power partition, calculate the ratio of its data volume to the total active power data volume, and eliminate the partitions with a ratio less than the preset ratio threshold. For the remaining power partitions, use the kernel density estimation algorithm to calculate the maximum - probability power and maximum - probability speed corresponding to each partition;

[0050] Fit a power - speed curve using the maximum - probability power and maximum - probability speed corresponding to each partition; where the abscissa of the curve is the active power and the ordinate is the generator speed.

[0051] On the other hand, the present invention also provides an electronic device, which includes a processor and a memory; wherein, at least one instruction is stored in the memory, and the instruction is loaded and executed by the processor to implement the above - mentioned method.

[0052] On another hand, the present invention also provides a computer - readable storage medium, in which at least one instruction is stored, and the instruction is loaded and executed by the processor to implement the above - mentioned method.

[0053] The technical solution provided by the present invention is dedicated to the numerical calculation of the actual speed parameters of a wind turbine generator set, and strives to efficiently utilize the SCADA data of the wind turbine generator set to carry out numerical calculations on the grid - connection speed and rated speed of the generator of the wind turbine generator set, and effectively solve the problems that the "visual inspection method" is not accurate enough and cannot be automated.

[0054] The beneficial effects brought by the technical solution provided by the present invention at least include:

[0055] 1. The present invention specifically selects the data corresponding to the power interval. For example, when obtaining the rated speed, select the data corresponding to the power interval not less than 80% of the maximum power; when obtaining the grid - connection speed, select the data corresponding to the power interval not higher than 2% of the maximum power. The targeted selection of the power interval largely avoids the influence of abnormal data of the unit on the calculation result.

[0056] 2. For the rated speed and grid - connection speed in the present invention, both are calculated by two algorithms respectively, that is, obtaining the maximum speed value by power partition and introducing KDE in the speed partition to obtain the maximum - probability speed value, and then comparing and determining the results calculated by the two methods, which further improves the accuracy of the results and the adaptability of the calculation method.

[0057] 3. The present invention introduces the zonal probability and the KDE algorithm to fit the rotational speed curve and thus generates various application methods: on the one hand, it can determine whether there is an abnormality between the generator rotational speed of the unit and the corresponding output power (judged by whether the rotational speed curve is smooth); on the other hand, by longitudinally comparing the rotational speed curves of the unit over time, it can be judged whether there is deterioration over time in the generator rotational speed and the corresponding output power; finally, by horizontally comparing the rotational speed curves of different units of the same model, the differences between the units and whether there are batch quality problems can be judged. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following-described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0059] Figure 1 is a schematic execution flow diagram of a numerical calculation method for the generator rotational speed parameters of a wind turbine unit provided by an embodiment of the present invention;

[0060] Figure 2 is a schematic flow diagram of fitting a rotational speed curve provided by an embodiment of the present invention;

[0061] Figure 3 is a schematic diagram of the calculation results of the rotational speed parameters of a normally operating doubly-fed asynchronous generator set provided by an embodiment of the present invention;

[0062] Figure 4 is a schematic diagram of the calculation results of the rotational speed parameters of a doubly-fed asynchronous generator set during the commissioning period provided by an embodiment of the present invention;

[0063] Figure 5 is a schematic diagram of the calculation results of the rotational speed parameters of a normally operating direct-drive synchronous generator set provided by an embodiment of the present invention;

[0064] Figure 6 is a schematic diagram of the calculation results of the rotational speed parameters of an abnormally operating direct-drive synchronous generator set provided by an embodiment of the present invention;

[0065] Figure 7 is a schematic diagram of the fitting of a rotational speed curve provided by an embodiment of the present invention;

[0066] Figure 8 is a schematic diagram of the comparison of the rotational speed curves of multiple units of the same model (showing the consistency of normal units) provided by an embodiment of the present invention;

[0067] Figure 9 is a schematic diagram of the comparison of the rotational speed curves of multiple units of the same model (comparing normal units with abnormal units) provided by an embodiment of the present invention;

[0068] Figure 10 is a system block diagram of an electronic device provided by an embodiment of the present invention;. DETAILED DESCRIPTION

[0069] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0070] First of all, it should be noted that in the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "exemplarily" is intended to present the concept in a concrete way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0071] First embodiment

[0072] This embodiment provides a method for numerically calculating the speed parameters of a wind turbine generator, which uses the actual operation data of the wind turbine to numerically calculate the actual grid-connected speed and rated speed of the wind turbine generator. The method can be implemented by an electronic device, which can be a terminal or a server. The method includes the following steps:

[0073] 1. Obtain the operating data of wind turbines;

[0074] It should be noted that, currently, wind farms widely use SCADA (Supervisory Control And Data Acquisition) systems to collect and record wind turbine operation data, including power, generator speed, wind speed, wind direction, blade angle and other parameters. In this regard, this embodiment selects active power data and generator speed data recorded by the SCADA system as processing objects.

[0075] In addition, it should be noted that the grid connection speed and rated speed of a wind turbine are two important indicators. The generator speed data recorded by the SCADA system are a series of discrete data from 0 to the maximum speed, and the speed sensor may also record incorrect data due to malfunctions. Therefore, it is impossible to directly obtain the specific values of the grid connection speed and rated speed of the generator from the recorded speed data, and statistical analysis and processing are required. Traditionally, by plotting the speed data against the power data or the speed data against the wind speed data as an XY scatter plot, the grid connection speed and rated speed of the generator are estimated by observing the data concentration band in the scatter plot, and whether there are any abnormalities in the generator speed is observed. This method is commonly used for the cause analysis when the output of the wind turbine is abnormal. However, this method is inaccurate on the one hand and cannot be applied to scenarios that require automatic analysis or batch calculation on the other hand.

[0076] To address the above problems, in this embodiment, the data is partitioned, the maximum value and maximum probability value of each partition are obtained, etc., the grid connection speed and rated speed are comprehensively obtained, and a speed curve is plotted to detect whether the generator speed is normal.

[0077] 2. Calculate the rated speed of the wind turbine based on the operating data;

[0078] It should be noted that a wind turbine has a speed range. The rated speed is generally approximately equal to the maximum speed of the wind turbine, and the speed at which the wind turbine outputs its maximum power generally also corresponds to the rated speed of the generator. However, the power output by the generator at the rated speed does not only correspond to the maximum power of the wind turbine but rather corresponds to a relatively wide power range; in addition, it cannot be simply assumed that the speed corresponding to the maximum power is directly equal to the rated speed of the generator because there may be some abnormal scatter points during the SCADA recording process. For this reason, the concept of partitioning needs to be introduced and the influence of abnormal data eliminated. The specific calculation process is as Figure 1 shown and includes:

[0079] S1: Extract the active power data {P i} and generator speed data {R i} with a time resolution of 10 minutes recorded by the SCADA to form a data set S = {(P i, R i )}, eliminate the data corresponding to P i ≤0, and calculate the maximum active power value MP = max(P i ) and the maximum generator speed value MR = max(R i ).

[0080] S2: Screen out the SCADA data corresponding to P i > 0.8MP, and equally divide the data into 10 intervals I j, j = 1, 2, ..., 10. For each power interval I j , find the maximum rotational speed MR_I of this interval j .

[0081] MR_I j = max(R i ) R i ∈I j (1)

[0082] S3: Form a set {MR_I j} with the 10 calculated MR_I j values, and re - sort them from smallest to largest to get [MR_I1, MR_I2, ..., MR_I 10 , where MR_I1 ≤ MR_I2 ≤ ... ≤ MR_I 10 .

[0083] S4: To avoid the influence of abnormal data, eliminate the first 2 and the last 2 of the 10 values, and finally 6 data {MR_I3, MR_I4, MR_I5, MR_I6, MR_I7, MR_I8} remain.

[0084] S5: Average the 6 data, that is, obtain the average maximum rotational speed of the generator in the [0.8MP, MP] interval, denoted as R1:

[0085]

[0086] Thus, a rated rotational speed R1 is obtained from the power dimension.

[0087] S6: Divide the rotational speed {R i} into equal - sized partitions to obtain a partition set {K i}. When partitioning, according to the MR value, set an appropriate partition step size so that the number of partitions m satisfies 10 ≤ m ≤ 300. For example, assume a direct - drive synchronous wind turbine with an MR of 17 rpm, the step size can be set to 1 rpm (rpm is the rotational speed unit, revolutions per minute); for another doubly - fed asynchronous wind turbine with an MR of 1800 rpm, the step size can be set to 10 rpm.

[0088] S7: For each rotational speed partition K j , calculate the ratio of the data volume of this partition to the total rotational speed data volume, and eliminate the partitions with a ratio less than 1% to reduce the influence of abnormal data such as jumps.

[0089] S8: For the remaining rotational speed partitions K j , use the kernel density estimation (KDE) algorithm to calculate the maximum probability rotational speed MR_K j, the kernel density estimation (KDE) algorithm is a commonly used non-parametric estimation method. It estimates the probability density by smoothing the sample data. When calculating, the Gaussian function is selected as the kernel function, and the standard deviation of the data is used as the bandwidth. Therefore, the probability density function is:

[0090]

[0091] In the formula, is the value of the probability density function estimated at the data point x, n is the amount of data, and σ is the bandwidth (here it is the standard deviation of the data).

[0092] MR_K j is K j partition maximum The corresponding rotational speed value.

[0093] S9: Obtain the maximum rotational speed of all rotational speed partitions, denoted as R2:

[0094] R2 = Max(MR_K j ) (4)

[0095] So far, a rated rotational speed value is obtained from the rotational speed dimension.

[0096] S10: Finally, the rated rotational speed R of the generator rated takes the maximum value of the above two rotational speed values, specifically:

[0097] R rated = max(R1, R2) (5)

[0098] 3. Calculate the grid connection rotational speed of the wind turbine based on the said operating data;

[0099] Among them, it should be noted that the grid connection rotational speed is the critical rotational speed of the generator when the wind turbine is grid-connected for power generation. Since the grid connection rotational speed corresponds to the moment when the wind turbine just starts grid-connected power generation, the corresponding power is not high. Based on this characteristic, it seems that the maximum probability value of the rotational speed of the generator in a very small power interval near 0 power can be calculated as the grid connection rotational speed, just like when dealing with the rated rotational speed as described above. However, through the actual measurement of a large amount of actual data of different models in different wind farms, it is found that relying solely on this method has great drawbacks. First, there are abnormal data with extremely high rotational speeds in the interval near 0 power for the units of some manufacturers (perhaps due to sensor abnormalities, grid connection commissioning, etc.); second, even for normal units, the rotational speed concentration band in the small interval near 0 power is not at the grid connection rotational speed, but is more concentrated at the rotational speed before grid connection startup. Therefore, the maximum density rotational speed value corresponding to the small interval near 0 power cannot be used as the grid connection rotational speed value.

[0100] After observing and analyzing a large amount of unit data from different manufacturers and different models, it is found that the grid connection speed of the generator accounts for a relatively large proportion in the entire speed range of the generator. To accurately calculate the grid connection speed of the generator, the present invention proposes the following method: First, calculate the maximum speed within 2% of the maximum power (note that it is not the maximum probability speed); secondly, find the speed range that satisfies the corresponding speed conditions and power conditions, and calculate its maximum probability speed; finally, take the smaller value of the speeds obtained by the two methods as the grid connection speed. The specific calculation process is as Figure 1 shown, including:

[0101] S1: Extract the active power data {P i} and the generator speed data {R i} with a time resolution of 10 minutes from the SCADA records, and form a data set S = {(P i, R i )}. Eliminate the data corresponding to P i ≤0, and calculate the value of the maximum active power MP = max(P i ) and the maximum generator speed value MR = max(R i ).

[0102] S2: Screen out the SCADA data where P i <0.02MP, and equally divide the data into 10 intervals J k , k = 1, 2,..., 10. For each interval J k , obtain the maximum speed MR_J k of this interval.

[0103] S3: Form a set {MR_J k} with the 10 calculated MR_J k values, and re - sort them from smallest to largest to get [MR_J1, MR_J2,..., MR_J 10 , where MR_J1 ≤ MR_J2 ≤... ≤ MR_J 10 .

[0104] S4: To avoid the influence of abnormal data, eliminate the first 2 and the last 2 of the 10 values, and finally the remaining 6 data {MR_J3, MR_J4, MR_J5, MR_J6, MR_J7, MR_J8} are left.

[0105] S4: Average the 6 data to obtain the maximum average speed of the generator in the [0, 0.02MP] interval, denoted as R3:

[0106]

[0107] So far, a grid connection speed value R3 has been obtained from the power dimension.

[0108] S5: Divide the rotational speed {R i} into equal partitions, and it is advisable that the number of partitions m satisfies 10 ≤ m ≤ 300.

[0109] S6: For each rotational speed partition K j , calculate the data volume occupancy ratio ρ_K j , the most probable rotational speed MR_K j and the most probable active power MP_K j . Among them, the calculations of MR_K j and MP_K j both adopt the kernel density estimation (KDE) algorithm. When calculating, the Gaussian function is selected as the kernel function, and the standard deviation of the data is used as the bandwidth. See Equation (3) for details.

[0110] The calculation of the data volume occupancy ratio ρ_K j is as follows:

[0111]

[0112] where, n_K j is the data volume contained in the rotational speed partition K j , and N is the total data volume of all partitions:

[0113] N = ∑n_K j (8)

[0114] S7: Re - sort the set of rotational speed partitions {K j} from largest to smallest according to the occupancy ratio ρ_K j

[0115] S8: Find the first partition K t that satisfies the following conditions:

[0116] (1) The most probable rotational speed of this partition is less than 0.75 * MR;

[0117] (2) The most probable active power of this partition is less than 0.2 * MP.

[0118] The formula representation of the above conditions is:

[0119] MR_K t ≤ 0.75 × MR and MP_K t ≤ 0.2 × MP (9)

[0120] S9: The most probable rotational speed of partition K t , denoted as R4.

[0121] R4 = MR_K t (10)

[0122] At this point, a grid-connected speed value R4 is also obtained from the speed probability dimension.

[0123] S10: Finally, the grid-connected speed of the generator takes the smaller value of the above two grid-connected speed values, specifically:

[0124] R cutin =min(R3,R4) (11)

[0125] 4. Perform speed curve fitting based on the operating data to obtain a speed curve;

[0126] It should be noted that the speed curve can be used to determine whether the speed of the generator matches the output power, and further determine whether the generator is normal. In this regard, this embodiment proposes to use the maximum probability density method to fit the power-speed curve or the speed-power curve. The two methods are the same, and only the parameters of the bins need to be swapped.

[0127] The following uses the power-speed curve as an example to illustrate the speed curve fitting process. Figure 2 As shown, including:

[0128] S1: Extract active power data with a time resolution of 10 minutes recorded by SCADA {P i} and generator speed data {R i}, forming a data set S = {(P i, R i )}, and remove P i Data corresponding to ≤0.

[0129] S2: Active power data {P i} is partitioned into equal parts, with a step size of 50kW or 100kW, and a power partition set {U i}.

[0130] S3: For each power partition U j , calculate the ratio of the data volume of the partition to the total active power data volume, eliminate the partitions with a ratio less than 1%, and reduce the impact of abnormal data such as jumps.

[0131] S4: For the remaining power partition U j , use the kernel density estimation (KDE) algorithm to calculate the maximum probability power MP_U corresponding to each interval i and the maximum probability speed MR_U j , each interval gets a data pair (MP_U i ,MR_U j ).

[0132] S5: All power zones U jThe above data pairs form a set Ps. Through this set, the rotational speed curve can be fitted. When fitting, the spline values for interpolation can be selected according to whether a smooth curve is required.

[0133] Ps = {(MP_U i , MR_U j )} (12)

[0134] Whether there is an abnormality between the generator rotational speed and output power of the unit can be judged from whether the fitted rotational speed curve is smooth; between different units of the same model, the rotational speed curves can be compared to determine whether there are significant differences between the units, thereby helping to judge the quality reliability of the units of this model; for the same unit, the rotational speed curves in different operation periods (such as the 1st year of operation, the 2nd year of operation, the 3rd year of operation,..., when leaving the warranty period) can be compared to judge whether there is a quality decline in the generator of the unit.

[0135] Next, the effectiveness of the method of the present invention will be verified through actual cases.

[0136] Case 1: Doubly-fed induction generator unit in normal operation

[0137] Taking a 5MW unit in a certain wind farm as an example, the rated power of this unit is 5000kW, the rated wind speed is 9.5m / s, the generator grid-connected rotational speed is 1050rpm, and the generator rated rotational speed is 1750rpm. The operating data such as active power and generator rotational speed recorded by the SCADA system of the unit for a complete year are selected. The sampling frequency is 10 minutes, and there are a total of 50509 data. After excluding the data with power less than or equal to 0, there are still 34506 left.

[0138] Four rotational speed data are calculated according to the method of the present invention:

[0139] R1 = 1751.62rpm

[0140] R2 = 1749.71rpm

[0141] R3 = 1050.17rpm

[0142] R4 = 1050.21rpm

[0143] It can be seen from the above data that for the unit in normal operation, R1 and R2 are close, and R3 and R4 are close, indicating that the results are similar for different numerical calculation methods. According to formula (5) and formula (11), the actual rated rotational speed of the generator of this unit is 1751.62rmp, and the actual grid-connected rotational speed is 1050.17rpm, which conforms to the design parameters, as Figure 3 shown.

[0144] Case 2: Doubly-fed induction generator unit during the commissioning period

[0145] Taking a 6.25MW unit in a wind farm as an example, the rated power of this unit is 6250kW, the rated wind speed is 9.5m / s, the grid-connected speed of the generator is 1080rpm, and the rated speed of the generator is 1780rpm. Select the SCADA system data of the unit during the trial operation period of less than 2 months, including active power, generator speed, etc. The sampling frequency is 10 minutes, with a total of 7966 data points. After removing the data with power less than or equal to 0, there are still 5567 left.

[0146] Four speed data are calculated according to the method of the present invention:

[0147] R1 = 1776.50rpm

[0148] R2 = 1651.00rpm

[0149] R3 = 1667.14rpm

[0150] R4 = 1078.00rpm

[0151] From the above data, it can be seen that for the unit during the trial operation period, due to unstable operation and the need for debugging, etc., there are a large number of abnormal data in the SCADA records, resulting in significant differences in the speed values calculated by different methods. For example, the R2 value of 1651.00rpm has a large difference from the designed rated speed parameter of 1780rpm. Since R2 is obtained by the maximum probability method, it indicates that the generator speed during the debugging period has not been fully released; the R3 value of 1667.14rpm has an even more obvious difference from the designed grid-connected speed of 1080rpm. Since R3 is obtained by the maximum value method, it indicates that there are a large number of high-speed abnormal scatter points near 0 power during the debugging period, which may be caused by reasons such as trial operation or speed sensor debugging.

[0152] Although there are obvious differences between R1 and R2, and between R3 and R4, the correct actual rated speed data and grid-connected speed data are still obtained by taking the maximum and minimum values respectively, which are 1776.5rpm and 1078.0rpm respectively, meeting the design parameters, as Figure 4 shown.

[0153] Case 3: Normal operation of a direct-drive synchronous generator set

[0154] Both Case 1 and Case 2 are doubly-fed induction generator sets. This type of generator set uses a variable-speed gearbox to convert the low speed of the impeller into a high speed to drive the generator, and the generator speed is relatively high. While the direct-drive synchronous generator set has no gearbox structure, and the generator speed is equal to the impeller speed. Therefore, the speed is relatively low. Taking a 1.55 MW generator set in a certain wind farm as an example, the rated power of this generator set is 1550 kW, the rated wind speed is 11.1 m / s, the grid-connected speed of the generator is 9.9 rpm, the rated speed of the generator is 17.3 rpm. The SCADA system data of the generator set for about 5 months is selected, including active power, generator speed, etc. The sampling frequency is 10 minutes, and there are a total of 20,676 pieces of data. After removing the data with power less than or equal to 0, there are still 19,748 pieces left.

[0155] Four speed data are calculated according to the method of the present invention:

[0156] R1 = 17.19

[0157] R2 = 17.07

[0158] R3 = 9.96

[0159] R4 = 9.88

[0160] From the above values, it can be seen that for a normally operating synchronous generator set, R1 and R2 are close, and R3 and R4 are close, indicating that different numerical calculation methods have similar results. According to formula (5) and formula (11), the actual rated speed of the generator of this generator set is obtained as 17.19 rmp, and the actual grid-connected speed is 9.88 rpm, which meets the design parameters, as Figure 5 shown.

[0161] Case 4: Abnormally operating direct-drive synchronous generator set

[0162] Taking a 4.5 MW direct-drive synchronous generator set in a certain wind farm as an example, the rated power of this generator set is 4500 kW, the rated wind speed is 10.8 m / s, the grid-connected speed of the generator is 6.0 rpm, the rated speed of the generator is 9.5 rpm. The SCADA system data of the generator set for about 5 months is selected, including active power, generator speed, etc. The sampling frequency is 10 minutes, and there are a total of 20,543 pieces of data. After removing the data with power less than or equal to 0, there are still 14,269 pieces left.

[0163] Four speed data are calculated according to the method of the present invention:

[0164] R1 = 9.53 rpm

[0165] R2 = 9.50 rpm

[0166] R3 = 6.00 rpm

[0167] R6 = 6.01 rpm

[0168] According to formula (5) and formula (11), the actual rated speed of the generator of this unit is obtained as 9.53 rmp, and the actual grid-connected speed is 6.0 rpm, which meets the design parameters, as Figure 6 shown. Therefore, even for units with abnormal operation, the method of the present invention can still accurately calculate the grid-connected speed and rated speed of the generator.

[0169] Examples 1 to 4 prove that the method of the present invention has strong adaptability and can adapt to various generator working conditions. On the one hand, according to the power characteristics corresponding to the rated speed and grid-connected speed, the method of the present invention selects a targeted power range, which can largely avoid the abnormal data range; on the other hand, the method of the present invention respectively obtains the maximum speed value in the power range and the maximum probability speed value in the speed range, and then compares and verifies, further avoiding the influence of abnormal data.

[0170] Example 5: Fitting and comparison of speed curves

[0171] Taking the unit in Example 1 as an example, the speed curve is fitted by the method of the present invention, as Figure 7 shown. The curve is smoothed and interpolated, and the interpolation spline value is 3. From Figure 7 it can be seen that the scatter concentration of the power and speed of the example unit is normal, there are few abnormal scatter points, and the fitted speed curve is smooth without large protrusions or mutations.

[0172] Figure 8 What is shown is the comparison of speed curves between units of the same model in this wind farm. From Figure 8 it can be seen that the speed curves of this type of unit basically coincide, and each unit maintains excellent stability and consistency during operation, indicating that the units of this model are of reliable and stable quality.

[0173] Figure 9 What is shown is the speed curve graph of 4.5 MW direct-drive units in another wind farm. The data source is about 5 operating months. From Figure 9 it can be seen that except for Unit F02, there are problems between the generator speed and its output power of the other units. Since the same problem appears in multiple units of the same model, it is necessary to check whether there are batch problems, providing a basis for the maintenance personnel to conduct troubleshooting.

[0174] By comparing Figure 8 and Figure 9 it can be known that for a unit with normal operation, its generator speed curve is smooth. If the speed curve shows a mutation, it indicates that there is a problem between the generator speed and output power of the unit, and problem troubleshooting is required.

[0175] In summary, this embodiment provides a numerical calculation method for the generator speed parameters of a wind turbine. According to the operation data recorded by SCADA, the grid connection speed, rated speed of the wind turbine generator set, and fitting the generator speed curve are calculated by using the partition maximum value and the partition maximum probability value, etc. When calculating, the data corresponding to the power interval is targeted selected according to whether the rated speed or the grid connection speed is calculated, which can greatly avoid the influence of abnormal data of the unit; and by obtaining the maximum speed value through power partitioning, introducing KDE in the speed partition to obtain the maximum probability speed value, and then comparing and judging the results calculated by the two methods, the accuracy of the results and the adaptability of the calculation method can be further improved; solving the problems that the "visual inspection method" is not accurate enough and cannot be automated, etc.

[0176] Second Embodiment

[0177] This embodiment provides an electronic device, as Figure 10 shown. The electronic device includes: a processor and a memory; wherein, the processor and the memory can be connected through a communication bus; at least one instruction is stored in the memory, and the instruction is loaded and executed by the processor to implement the method of the above first embodiment. In addition, the electronic device may further include a transceiver, the processor and the transceiver can be connected through a communication bus, and the transceiver is used for communicating with other devices.

[0178] Next, in combination with Figure 10 specifically introduce each component of the electronic device:

[0179] Among them, the processor is the control center of the electronic device. The electronic device may include multiple processors, and each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may be a single processor or a collective term for multiple processing elements. For example, the processor may be one or more central processing units (CPUs), or other general-purpose processors, application specific integrated circuits (ASICs), or one or more integrated circuits configured to implement the embodiments of the present invention. For example: one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor can execute various functions of the electronic device by running or executing software programs stored in the memory and calling data stored in the memory.

[0180] In a specific implementation, as an embodiment, the processor may include one or more CPUs. For example Figure 10 CPU0 and CPU1 shown in, of course, this is only an exemplary illustration.

[0181] The memory is used to store the software program for executing the solution of the present invention and is controlled by the processor for execution. The specific implementation manner may refer to the above method embodiments and will not be elaborated here.

[0182] Optionally, the memory may be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may be integrated with the processor or exist independently and be coupled to the processor through the interface circuit of the electronic device ( Figure 10 not shown in the figure), and the embodiments of the present invention do not make specific limitations in this regard.

[0183] The transceiver may include a receiver and a transmitter ( Figure 10 not shown separately). Among them, the receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function. The transceiver may be integrated with the processor or exist independently and be coupled to the processor through the interface circuit of the electronic device ( Figure 10 not shown in the figure), and the embodiments of the present invention do not make specific limitations in this regard.

[0184] In addition, it should be noted that Figure 10 the structure of the electronic device shown in the figure does not constitute a limitation on the device. The actual device may include more or fewer components than shown in the figure, or combine certain components, or have a different component layout. In addition, the technical effects achieved by the electronic device when executing the method of the first embodiment above may refer to the technical effects described in the first embodiment above, so they will not be elaborated here.

[0185] Third Embodiment

[0186] This embodiment provides a computer-readable storage medium, in which at least one instruction is stored, and the instruction is loaded and executed by a processor to implement the method of the first embodiment above. Among them, the computer-readable storage medium may be ROM, random access memory, CD-ROM, magnetic tape, floppy disk, and optical data storage devices, etc. The instructions stored therein can be loaded and executed by the processor in the terminal to execute the above method.

[0187] In addition, it should be noted that the present invention can be provided as a method, apparatus, or computer program product. Therefore, the embodiments of the present invention can take the form of all or part of a hardware embodiment, all or part of a software embodiment, or an embodiment combining software and hardware aspects. Moreover, when implemented using software, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present invention are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center containing one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0188] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing terminal device generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0189] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1the functions specified in one or more boxes. These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable terminal device provide for implementing the steps in the process Figure 1 one process or more processes and / or boxes Figure 1 for implementing the functions specified in one or more boxes.

[0190] It should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. The term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or terminal device comprising the said element. In addition, the term "and / or" is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this text generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship, which can be understood specifically with reference to the context. "At least one" means one or more, and "a plurality" means two or more. "At least one of the following (items)" or similar expressions refer to any combination of these items, including any combination of single (item) or plural (items). For example, at least one of a, b or c can mean: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, c can be single or multiple.

[0191] In addition, it can be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0192] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0193] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of functional modules / units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms. The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0194] If the method is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0195] Finally, it should be noted that the above description is only the preferred embodiment of the present invention. It should be pointed out that although the preferred embodiments of the present invention have been described, for those of ordinary skill in the art, once the basic creative concept of the present invention is known, several improvements and refinements can be made without departing from the principle of the present invention. These improvements and refinements should also be regarded as the protection scope of the present invention. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

Claims

1. A numerical calculation method for the speed parameters of a wind turbine generator, characterized in that: include: Acquire the operation data of the wind turbine generator set; wherein the operation data of the wind turbine generator set includes: active power data of the wind turbine generator set and generator speed data of the wind turbine generator set; Based on the operating data, calculating the rated speed of the wind turbine; Based on the operating data, calculating the grid-connected speed of the wind turbine generator; Based on the operating data, a speed curve is fitted to obtain a speed curve; wherein the speed curve is used to determine whether the speed of the generator matches the output power, and further determine whether the generator is normal.

2. The numerical calculation method of the speed parameter of the wind turbine generator according to claim 1, characterized in that: Based on the operating data, the rated speed of the wind turbine is calculated, including: Based on the operating data, a rated speed value R1 is obtained from the power dimension; Based on the operating data, a rated speed value R2 is obtained from the speed dimension; The maximum value of R1 and R2 is taken as the rated speed of the wind turbine.

3. The numerical calculation method of the speed parameter of the wind turbine generator according to claim 2, characterized in that: Based on the operating data, a rated speed value R1 is obtained from the power dimension, including: Extracting active power data and generator speed data with a time resolution of T minutes from the operating data, aligning the extracted active power data and generator speed data in the time dimension, and using the aligned active power data and generator speed data to form a first data set; removing active power data and its corresponding generator speed data that are not greater than 0 from the first data set to obtain a second data set; wherein T is a preset value; Active power data and corresponding generator speed data greater than a first preset power threshold value are screened out from the second data set, and the screened data are divided into N intervals according to the size of the active power, and for each divided interval, the maximum generator speed value is obtained; wherein N is a preset value; The calculated maximum generator speed values ​​of each interval are re-arranged in ascending order, and the sorted maximum generator speed values ​​of each interval form a third data set; Eliminate the first n and last n values ​​in the third data set to obtain a fourth data set, wherein n is a preset value; The average value of the data in the fourth data set is used as the rated rotation speed value R1 obtained from the power dimension.

4. The numerical calculation method of the speed parameter of the wind turbine generator according to claim 3, characterized in that: Based on the operating data, a rated speed value R2 is obtained from the speed dimension, including: The screened generator speed data is equally partitioned to obtain a plurality of speed partitions; wherein, when the screened generator speed data is equally partitioned, the number of speed partitions M needs to satisfy 10≤M≤300; For each speed partition, calculate the ratio of the amount of data in it to the amount of data of all generator speeds; The speed partitions whose ratio is less than the preset ratio threshold are eliminated; for the remaining speed partitions, the maximum probability speed of each speed interval is calculated using the kernel density estimation algorithm; The maximum value of all maximum probability rotational speeds is obtained as the rated rotational speed value R2 obtained from the rotational speed dimension.

5. The numerical calculation method of the speed parameter of the wind turbine generator according to claim 1, characterized in that: Based on the operating data, the grid-connected speed of the wind turbine generator is calculated, including: Based on the operating data, a grid-connected speed value R3 is obtained from the power dimension; Based on the operating data, a grid-connected speed value R4 is also obtained from the speed probability dimension; The minimum value of R3 and R4 is taken as the grid-connected speed of the wind turbine.

6. The numerical calculation method of the speed parameter of the wind turbine generator according to claim 5, characterized in that: Based on the operating data, a grid-connected speed value R3 is obtained from the power dimension, including: Extracting active power data and generator speed data with a time resolution of T minutes from the operating data, aligning the extracted active power data and generator speed data in the time dimension, and using the aligned active power data and generator speed data to form a fifth data set; removing active power data not greater than 0 and its corresponding motor speed data from the fifth data set to obtain a sixth data set; wherein T is a preset value; Filter out the active power data and the corresponding generator speed data that are less than the second preset power threshold in the sixth data set, and divide the filtered data into N intervals according to the size of the active power, and for each divided interval, obtain the maximum generator speed value therein; wherein N is a preset value; The calculated maximum generator speed values ​​of each interval are re-arranged in ascending order, and the maximum generator speed values ​​of each interval after the sorting are used to form a seventh data set; Eliminate the first n and last n values ​​in the seventh data set to obtain an eighth data set, wherein n is a preset value; The average value of the data in the eighth data set is used as the grid-connected speed value R3 obtained from the power dimension.

7. The numerical calculation method of the speed parameter of the wind turbine generator according to claim 6, characterized in that: Based on the operating data, a grid-connected speed value R4 is also obtained from the speed probability dimension, including: The screened generator speed data is equally partitioned to obtain a plurality of speed partitions; wherein, when the screened generator speed data is equally partitioned, the number of speed partitions M needs to satisfy 10≤M≤300; For each speed partition, the ratio of the data volume in it to the total generator speed data volume is calculated, and the maximum probability speed and maximum probability active power of each speed interval are calculated using the kernel density estimation algorithm; reordering the speed partitions from largest to smallest according to the ratio; Filter out the first partition K that meets the following conditions from the sorted speed partitions: t : (1) The maximum probability speed of the speed partition is less than 0.75*MR; (2) The maximum probability active power of the speed partition is less than 0.2*MP; Wherein, MP represents the maximum active power data in the sixth data set; MR represents the maximum generator speed data in the sixth data set; K t The maximum probability speed is taken as the grid-connected speed value R4 obtained from the speed probability dimension.

8. The numerical calculation method of the speed parameter of the wind turbine generator according to claim 1, characterized in that: Based on the operating data, a speed curve is fitted to obtain a speed curve, including: Extract active power data and generator speed data with a time resolution of T minutes from the operating data, align the active power data and generator speed data in the time dimension, and then remove the active power data and the corresponding motor speed data that are not greater than 0, to obtain a ninth data set; wherein T is a preset value; Partitioning the active power data in the ninth data set into equal parts to obtain a plurality of power partitions; For each power partition, calculate the ratio of its data volume to the total active power data volume, remove the partitions whose ratio is less than the preset ratio threshold, and for the remaining power partitions, use the kernel density estimation algorithm to calculate the maximum probability power and maximum probability speed corresponding to each partition; The power-speed curve is fitted using the maximum probability power and maximum probability speed corresponding to each partition; wherein the abscissa of the curve is the active power, and the ordinate is the generator speed.

Images