Optimization Method and Device for Wind Speed ​​Transfer Function of Wind Turbine Based on SCADA System

Abstract

This disclosure provides an embodiment of a method and apparatus for optimizing the wind speed transfer function of a wind turbine based on a SCADA system. The method includes: acquiring a standard power curve of the wind turbine; plotting a measured power curve of the wind turbine based on measured operating data; correcting the measured wind speed corresponding to the measured power on the measured power curve according to the standard power curve to obtain a corrected wind speed; restoring the measured wind speed according to the current wind speed transfer function to obtain the original wind speed; and obtaining a new wind speed transfer function based on the corrected wind speed and the original wind speed. In this way, dynamic evaluation and agile calibration of the wind speed transfer function of the wind turbine can be achieved based on its own measured power curve, ensuring that the wind speed transfer function can be updated in a timely manner according to the wind turbine's own operating conditions.

Description

Technical Field

[0001] This disclosure relates to the field of wind turbines, and more particularly to the field of wind speed transfer function technology. Background Technology

[0002] The wind speed transfer function (FSF) of a wind turbine refers to the relationship between the turbine's output power and wind speed, typically used to describe the energy conversion efficiency of a wind turbine at a specific wind speed. Existing wind turbines are generally equipped with a wind measurement system located behind the rotor. In the turbine's control logic, the measured incoming wind speed needs to be converted and corrected according to the set FSF to ensure that the measured wind speed data more closely matches the actual wind speed at the turbine's hub height in front of the rotor. However, in practice, a wind farm or a single turbine model often uses the same FSF. The fitting reference standard for this FSF is often selected from data from a limited number of wind measurement towers, and the fitting form of the FSF often adopts a fixed first-order linear (i.e., ax+b) mode. This results in inherent deviations between the wind speed value corrected by the FSF and the actual wind speed. Therefore, how to update the FSF in a timely and effective manner to ensure its accuracy has become a pressing issue. Summary of the Invention

[0003] This disclosure provides a method, apparatus, device, and storage medium for optimizing the wind speed transfer function of a wind turbine based on a SCADA system.

[0004] According to a first aspect of this disclosure, an optimization method for the wind speed transfer function of a wind turbine based on a SCADA system is provided. The method includes:

[0005] Obtain the standard power curve of the wind turbine, wherein the standard power curve is used to characterize the correspondence between standard power and standard wind speed;

[0006] Based on the measured operating data of the wind turbine, the measured power curve of the wind turbine is plotted, wherein the measured power curve is used to show the correspondence between measured power and measured wind speed.

[0007] Based on the standard power curve, the measured wind speed corresponding to the measured power on the measured power curve is corrected to obtain the corrected wind speed.

[0008] The measured wind speed is reconstructed based on the current wind speed transfer function to obtain the original wind speed;

[0009] Based on the corrected wind speed and the original wind speed, a new wind speed transfer function is obtained.

[0010] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the step of correcting the measured wind speed corresponding to the measured power on the measured power curve according to the standard power curve to obtain the corrected wind speed includes:

[0011] Based on the measured power on the measured power curve, match the minimum standard power range of the standard power curve in which it is located;

[0012] Determine the minimum standard wind speed range on the standard power curve that corresponds to the minimum standard power range;

[0013] The endpoint coordinates of the minimum standard power range and the endpoint coordinates of the minimum standard wind speed range are calculated using a preset interpolation method to obtain the corrected wind speed.

[0014] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the step of restoring the measured wind speed according to the current wind speed transfer function to obtain the original wind speed includes: performing a reverse transformation on the measured wind speed according to the current wind speed transfer function to obtain the original wind speed.

[0015] In addition to the aspects and any possible implementations described above, a further implementation is provided in which obtaining a new wind speed transfer function based on the modified wind speed and the original wind speed includes:

[0016] The corrected wind speed and the original wind speed are subjected to polynomial iterative fitting, and the coefficient of determination of each iterative fitting is obtained;

[0017] Obtain the preset iteration threshold;

[0018] The coefficient of determination of each iteration is compared with the preset iteration threshold. When the coefficient of determination is greater than the preset iteration threshold for the first time, the iterative fitting stops, and the polynomial at which the iterative fitting stops is taken as the new wind speed transfer function.

[0019] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the step of plotting the measured power curve of the wind turbine based on the measured operating data of the wind turbine includes:

[0020] Delete the missing data from the measured operating data of the wind turbine;

[0021] After deletion, the remaining measured operating data of the wind turbine will be sorted according to timestamps.

[0022] The first record of all duplicate data is retained sequentially to obtain the deduplicated test data.

[0023] The deduplicated measured operational data is then standardized in terms of type and unit.

[0024] Based on the standardized measured operating data, the measured power curve of the wind turbine was plotted.

[0025] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the method further includes:

[0026] Calculate the theoretical power generation of the wind turbine based on the standard power curve;

[0027] Based on the measured power curve, calculate the measured estimated power generation of the wind turbine.

[0028] Based on the theoretical power generation and the measured estimated power generation, determine whether to use the new wind speed transfer function to replace the current wind speed transfer function.

[0029] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein determining whether to replace the current wind speed transfer function with the new wind speed transfer function based on the theoretical power generation and the measured estimated power generation includes:

[0030] Calculate the current power generation ratio of the measured estimated power generation to the theoretical power generation;

[0031] Obtain the threshold for the proportion of power generation;

[0032] Calculate the absolute value of the difference between the current power generation ratio and 1;

[0033] If the absolute value of the difference is greater than the power generation ratio threshold, then it is determined that the new wind speed transfer function will be used to replace the current wind speed transfer function.

[0034] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the method further includes:

[0035] When the wind turbine units include multiple wind turbine units, each wind turbine unit has its own corresponding current wind speed transfer function and new wind speed transfer function.

[0036] If any of the multiple wind turbine units needs to replace its current wind speed transfer function with its new wind speed transfer function, then the new wind speed transfer function of the wind turbine unit is sent to the wind turbine unit.

[0037] According to a second aspect of this disclosure, an optimization device for the wind speed transfer function of a wind turbine based on a SCADA system is provided. The device includes:

[0038] The first acquisition module is used to acquire the standard power curve of the wind turbine, wherein the standard power curve is used to characterize the correspondence between standard power and standard wind speed;

[0039] The plotting module is used to plot the measured power curve of the wind turbine based on the measured operating data of the wind turbine, wherein the measured power curve is used to show the correspondence between the measured power and the measured wind speed.

[0040] The correction module is used to correct the measured wind speed corresponding to the measured power on the measured power curve according to the standard power curve, so as to obtain the corrected wind speed.

[0041] The restoration module is used to restore the measured wind speed according to the current wind speed transfer function to obtain the original wind speed;

[0042] The second acquisition module is used to acquire a new wind speed transfer function based on the corrected wind speed and the original wind speed.

[0043] According to a third aspect of this disclosure, an electronic device is provided. The electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the method described above.

[0044] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the method according to a first aspect of this disclosure.

[0045] In this disclosure, after obtaining the standard power curve and the measured power curve of the wind turbine, the measured wind speed corresponding to the measured power on the measured power curve can be corrected according to the standard power curve to obtain the corrected wind speed. Then, the measured wind speed is restored according to the current wind speed transfer function to obtain the original wind speed. Then, a new wind speed transfer function is obtained according to the corrected wind speed and the original wind speed. In this way, during the operation of the wind turbine, the wind speed transfer function of the wind turbine can be dynamically evaluated and calibrated agilely based on the wind turbine's own measured power curve. This ensures that the wind speed transfer function can be updated in a timely manner according to the wind turbine's own operating conditions, avoiding the inaccuracy of wind speed correction caused by the wind turbine always using a general and fixed wind speed transfer function, which is beneficial to improving the accuracy of wind speed correction of the wind turbine.

[0046] It should be understood that the description in the Summary of the Invention is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0047] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. The drawings are provided for a better understanding of the invention and are not intended to limit the scope of this disclosure. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0048] Figure 1 A flowchart is shown for an optimization method of wind speed transfer function of a wind turbine based on a SCADA system according to an embodiment of the present disclosure;

[0049] Figure 2 A flowchart is shown for another method for optimizing the wind speed transfer function of a wind turbine based on a SCADA system, according to an embodiment of the present disclosure.

[0050] Figure 3 A flowchart is shown for another method for optimizing the wind speed transfer function of a wind turbine based on a SCADA system, according to an embodiment of the present disclosure.

[0051] Figure 4 A schematic diagram illustrating the principle of correcting the measured wind speed corresponding to the measured power on the measured power curve according to the standard power curve, based on an embodiment of the present disclosure;

[0052] Figure 5 A schematic diagram of a wind speed transfer function after polynomial iterative fitting according to an embodiment of the present disclosure is shown.

[0053] Figure 6 A block diagram of a wind turbine wind speed transfer function device according to an embodiment of the present disclosure is shown;

[0054] Figure 7 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0056] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0057] Figure 3 A flowchart is shown of a method 300 for optimizing the wind speed transfer function of a wind turbine based on a SCADA system according to an embodiment of the present disclosure. Method 300 may include:

[0058] Step 310: Obtain the standard power curve of the wind turbine, wherein the standard power curve is used to characterize the correspondence between standard power and standard wind speed;

[0059] The standard power curve can be the design power curve, the contract power curve, or the guaranteed power curve. In short, it is a power curve that already exists before the wind turbine is put into actual operation. The power on this power curve is called the standard power, and the wind speed on this power curve is called the standard wind speed.

[0060] Specifically, it can be as follows:

[0061] Standard power curve data is derived from standard wind speed. and standard power Composed of two column vectors, defined as shown in formulas 1) to 3):

[0062] ,1)

[0063] ,2)

[0064] ,3)

[0065] Standard wind speed vector Includes the cut-in wind speed from the wind turbine. Cut-out wind speed The standard power vector is composed of n standard center wind speed values ​​spaced at intervals of 0.5 m / s and their corresponding power values ​​according to the unit's design power curve (contract power curve, guaranteed power curve). Generally, the standard wind turbine design power curve, contract power curve, and guaranteed power curve data can all be provided in advance and directly read and applied when needed. Among them, the wind speed unit of the standard power curve is m / s, and the power unit is usually kW. After desensitization and normalization, it is a proportional value between 0 and 1.

[0066] Step 320: Based on the measured operating data of the wind turbine, plot the measured power curve of the wind turbine, wherein the measured power curve is used to show the correspondence between measured power and measured wind speed;

[0067] The measured operating data of the wind turbine includes many data points, each of which includes: wind speed, active power, generator speed, pitch angle, and operating status flags.

[0068] The time span of the measured operating data should be between 6 months and 1 year, and not less than 3 months. At the same time, the normal operating time of the unit connected to the grid during the evaluation period should be no less than 180 hours.

[0069] Generally, the statistical calculation results of the measured power curve are derived from the measured wind speed. (Wind speed measured by the anemometer system behind the impeller) and measured power It consists of two column vectors, defined as shown in formulas 4) and 5):

[0070] ,4)

[0071] ,5)

[0072] Measured wind speed n consecutive wind speed intervals are defined with an upper and lower limit of 0.25 m / s for each standard center wind speed. Based on this, the measured wind speed value within each interval is defined as the average wind speed of all 10-minute averaged segments of the measured operational data falling within that interval. Simultaneously, the average power value corresponding to each interval is defined as the measured power value within that interval. Here, the unit for measured wind speed is m / s, and the unit for measured power is kW; after desensitization and normalization, these are also proportional values.

[0073] Step 330: Based on the standard power curve, correct the measured wind speed corresponding to the measured power on the measured power curve to obtain the corrected wind speed;

[0074] Step 340: Reconstruct the measured wind speed based on the current wind speed transfer function to obtain the original wind speed;

[0075] Given the measured wind speed in the wind turbine SCADA system The current wind speed transfer function has been passed. Therefore, before fitting a new wind speed transfer function, the measured wind speed must be converted. According to the current wind speed transfer function Reverse transformation to original wind speed Given the original wind speed polynomial and the measured wind speed. The functional relationship between them is defined as in Formula 8:

[0076]

[0077] ,8)

[0078] Currently, most existing wind turbine technologies use a first-order linear wind speed transfer function, i.e., second-order and above, up to the kth-order coefficients in Equation 8. The polynomials that are all equal to 0 are used in this invention, while the wind speed transfer function used in this invention is a multi-order polynomial form, the specific order of which can be determined by training results. Therefore, given the current wind speed transfer function... Measured wind speed in SCADA system In this case, the original wind speed vector can be deduced by using the inverse function of Formula 8. The numerical values ​​are given. Here, the inverse transformation based on the first-order linear wind speed transfer function is easily implemented, while the inverse transformation of second-order and higher polynomials can be quickly implemented using the polynomial processing capabilities provided by Python, R, etc. As shown in Equation 9, the original wind speed vector after the inverse transformation is defined. (i.e., the vector formed by the original wind speed) (The original wind speed corresponding to the i-th measured wind speed in the actual operation data).

[0079] ,9)

[0080] Step 350: Obtain a new wind speed transfer function based on the corrected wind speed and the original wind speed. After obtaining the standard power curve and the measured power curve of the wind turbine, the measured wind speed corresponding to the measured power on the measured power curve can be corrected according to the standard power curve to obtain the corrected wind speed. Then, the measured wind speed is restored according to the current wind speed transfer function to obtain the original wind speed. Finally, a new wind speed transfer function is obtained based on the corrected wind speed and the original wind speed. In this way, during the operation of the wind turbine, the wind speed transfer function of the wind turbine can be dynamically evaluated and agilely calibrated based on the wind turbine's own measured power curve. This ensures that the wind speed transfer function can be updated in a timely manner according to the wind turbine's own operating conditions, avoiding the inaccuracy of wind speed correction caused by the wind turbine always using a general and fixed wind speed transfer function, and improving the accuracy of wind speed correction of the wind turbine.

[0081] The standard power curve, measured operating data, current wind speed transfer function, and new wind speed transfer function are all stored in the SCADA system.

[0082] SCADA systems can be installed on servers.

[0083] In some embodiments, the step of correcting the measured wind speed corresponding to the measured power on the measured power curve according to the standard power curve to obtain the corrected wind speed includes:

[0084] Based on the measured power on the measured power curve, match the minimum standard power range of the standard power curve in which it is located;

[0085] Determine the minimum standard wind speed range on the standard power curve that corresponds to the minimum standard power range;

[0086] The endpoint coordinates of the minimum standard power range and the endpoint coordinates of the minimum standard wind speed range are calculated using a preset interpolation method to obtain the corrected wind speed.

[0087] For each measured power on the measured power curve, the minimum standard power interval of the standard power curve to which it belongs can be matched. Then, the minimum standard wind speed interval corresponding to the minimum standard power interval on the standard power curve is found. Then, the endpoint coordinates of the minimum standard power interval and the endpoint coordinates of the minimum standard wind speed interval are interpolated to obtain the corrected wind speed corresponding to each measured power on the measured power curve, so as to ensure the accuracy of the corrected wind speed.

[0088] The specific principle for obtaining the corrected wind speed is as follows:

[0089] The i-th measured power value for each measured power curve is The minimum standard power range that matches the standard power curve in which it is located. The minimum standard wind speed and the minimum standard power corresponding to the minimum standard power range are selected as the coordinates of the two endpoints of the corrected interpolation segment. and The measured power value can be calculated using the linear relationship within this interval. Correct the wind speed according to the standard power curve And define the corrected wind speed vector as :

[0090]

[0091]

[0092]

[0093]

[0094] The cut-in wind speed for the wind turbine. This refers to the cut-out wind speed of the wind turbine.

[0095] The coordinates of the endpoints of the minimum standard power range are

[0096] The coordinates of the endpoints of the minimum standard wind speed range are

[0097] In some embodiments, the current wind speed transfer function is a preset polynomial with the original wind speed as the independent variable and the measured wind speed as the dependent variable; the step of restoring the measured wind speed according to the current wind speed transfer function to obtain the original wind speed includes: performing a reverse transformation on the measured wind speed according to the current wind speed transfer function to obtain the original wind speed.

[0098] Since the current wind speed transfer function is known, each coefficient in the preset polynomial is also known. Therefore, by substituting the measured wind speed into the preset polynomial and performing an inverse transformation, the corresponding original wind speed can be obtained.

[0099] In some embodiments, obtaining a new wind speed transfer function based on the corrected wind speed and the original wind speed includes:

[0100] The corrected wind speed and the original wind speed are subjected to polynomial iterative fitting, and the coefficient of determination of each iterative fitting is obtained;

[0101] Obtain the preset iteration threshold;

[0102] The coefficient of determination of each iteration is compared with the preset iteration threshold. When the coefficient of determination is greater than the preset iteration threshold for the first time, the iterative fitting stops, and the polynomial at which the iterative fitting stops is taken as the new wind speed transfer function.

[0103] By performing a polynomial iterative fitting on the corrected wind speed and the original wind speed, the coefficient of determination for each iteration can be obtained, and then the coefficient of determination can be used. As a statistical standard for quantifying the goodness of fit of polynomials of arbitrary order, a preset iteration threshold is obtained, and then the coefficient of determination of each iteration is compared with the preset iteration threshold until the coefficient of determination is greater than the preset iteration threshold for the first time. Then, the iteration fitting of higher orders is stopped, and the polynomial at which the iteration fitting stops is taken as the new wind speed transfer function. This method of obtaining a new wind speed transfer function by using multi-order polynomial curve fitting is obviously more able to focus on the inherent nonlinear characteristics of low and medium wind speed ranges than the linear function fitting method commonly used in existing methods. It significantly improves the accuracy and rationality of the fitting function, thereby ensuring the accuracy of the wind speed transfer function.

[0104] coefficient of determination Defined as the difference between 1 and the ratio of the sum of squared residuals (RSS) to the sum of squared mean errors (TSS). The normal range of values ​​is And the optimal value is 1, theoretically A larger value indicates a better fit. This invention specifies the coefficient of determination for fitting a polynomial of a certain order. First time greater than the decision threshold When the time is right, the higher-order polynomial fitting iteration can be stopped, and the polynomial of that order can be selected as the final fitting result of the new wind speed transfer function.

[0105]

[0106]

[0107]

[0108] To fit the corrected wind speed vector, For the i-th fitted correction wind speed, For the i-th corrected wind speed, This is the average of all corrected wind speeds.

[0109] In some embodiments, plotting the measured power curve of the wind turbine based on the measured operating data of the wind turbine includes:

[0110] Delete the missing data from the measured operating data of the wind turbine;

[0111] After deletion, the remaining measured operating data of the wind turbine will be sorted according to timestamps.

[0112] The first record of all duplicate data is retained sequentially to obtain the deduplicated test data.

[0113] The deduplicated measured operational data is then standardized in terms of type and unit.

[0114] Unit standardization can be achieved as follows:

[0115] Wind speed is measured in meters per second (m / s), power is measured in watts (W) or kilowatts (kW), angle is measured in degrees (°) or radians (rad), and rotational speed is measured in revolutions per minute (rpm) or radians per second (rad / s). Finally, the data timestamp is formatted in the standard format of year-month-day hour:minute:second (yyyy-mm-dd hh:mm:ss).

[0116] Based on the standardized measured operating data, the measured power curve of the wind turbine was plotted.

[0117] By deleting missing data from the measured operating data, it can be ensured that each data point in the remaining measured operating data is complete. By retaining the first record of all duplicate data in timestamp order, data redundancy can be avoided. Furthermore, by standardizing the data type and units of the deduplicated measured operating data, the accuracy of the measured power curve can be ensured.

[0118] In some embodiments, the method further includes:

[0119] Calculate the theoretical power generation of the wind turbine based on the standard power curve;

[0120] Based on the measured power curve, calculate the measured estimated power generation of the wind turbine.

[0121] Based on the theoretical power generation and the measured estimated power generation, determine whether to use the new wind speed transfer function to replace the current wind speed transfer function.

[0122] By integrating the standard power and time in the standard power curve, the theoretical power generation of the wind turbine can be obtained. Similarly, by integrating the measured power and time in the measured power curve, the measured estimated power generation of the wind turbine can be obtained. Then, the theoretical power generation and the measured estimated power generation are compared. The difference between the two determines whether to use the new wind speed transfer function to replace the current wind speed transfer function, so as to ensure the timely update of the wind speed transfer function. This helps to improve the accuracy of wind speed correction.

[0123] In some embodiments, determining whether to replace the current wind speed transfer function with the new wind speed transfer function based on the theoretical power generation and the measured estimated power generation includes:

[0124] Calculate the current power generation ratio of the measured estimated power generation to the theoretical power generation;

[0125] Current power generation ratio = quotient of actual estimated power generation and theoretical power generation.

[0126] Obtain the threshold for the proportion of power generation;

[0127] Calculate the absolute value of the difference between the current power generation ratio and 1;

[0128] If the absolute value of the difference is greater than the power generation ratio threshold, then it is determined that the new wind speed transfer function will be used to replace the current wind speed transfer function.

[0129] By calculating the current power generation ratio and then calculating the absolute value of the difference between the current power generation ratio and 1, it can be determined whether the absolute value of the power generation ratio is greater than the power generation ratio threshold. If the absolute value of the difference is greater than the power generation ratio threshold, it indicates that the current wind speed transfer function is inaccurate, causing the measured estimated power generation to be greater than the theoretical power generation or the measured estimated power generation to be far lower than the expected theoretical power generation. Therefore, a new wind speed transfer function needs to be used to replace the current wind speed transfer function to ensure that the wind speed transfer function of the wind turbine can be updated in a timely manner and that the wind speed transfer function is accurate.

[0130] In some embodiments, the method further includes:

[0131] When the wind turbine units include multiple wind turbine units, each wind turbine unit has its own corresponding current wind speed transfer function and new wind speed transfer function.

[0132] If any of the multiple wind turbine units needs to replace its current wind speed transfer function with its new wind speed transfer function, then the new wind speed transfer function of the wind turbine unit is sent to the wind turbine unit.

[0133] If there are multiple wind turbine units, the new wind speed transfer function for each wind turbine unit is calculated according to the above steps. If any wind turbine unit needs to replace the current wind speed transfer function with its new wind speed transfer function, the new wind speed transfer function of that wind turbine unit is sent to that wind turbine unit. This ensures that each wind turbine unit can update its wind speed transfer function in a timely manner when needed, rather than using an unchanging universal wind speed transfer function.

[0134] Specifically, this invention utilizes the communication function between the on-site SCADA system and the wind turbine control PLC to send the polynomial coefficients of the new wind speed transfer function from the SCADA system to the PLC receiving register, and automatically replaces the coefficient values ​​of the wind speed transfer function initialized by the PLC. Compared with existing methods, this invention can realize dynamic evaluation and agile calibration of the wind turbine wind speed transfer function.

[0135] The following will combine Figure 1 The optimization method for the wind speed transfer function of wind turbines based on SCADA systems of the present invention will be described as follows:

[0136] S101, this invention is based on an on-site SCADA system and uses wind turbine operating data to optimize the wind speed transfer function of the turbine. This invention directly reads the second-level time-series operating data of the wind turbine from the on-site SCADA system. The sampling period of the data specification cannot exceed 10 minutes. The data variables in the SCADA system participating in the optimization must include the wind speed, active power, generator speed, pitch angle, and operating status flags of the wind turbine. The time span of the data involved in the analysis should preferably be 6 months to 1 year, but not less than 3 months. Simultaneously, the normal operating time of the wind turbine's grid-connected section during the evaluation period should be no less than 180 hours.

[0137] S102 requires preprocessing the raw data to be evaluated (i.e., the measured operating data of the wind turbine) by cleaning, deduplication, and standardization of types and units. First, all data records containing missing values ​​are filtered and deleted row by row. Second, the first record of all duplicate data is retained in the order of data timestamps. Then, the data types of variables such as wind speed, active power, generator speed, and pitch angle are uniformly converted to floating-point (float) types, and the units of the data variables are standardized, such as wind speed in meters per second (m / s), power in watts (W) or kilowatts (kW), angle in degrees (°) or radians (rad), and speed in revolutions per minute (rpm) or radians per second (rad / s). Finally, the data timestamps are formatted in the standard format of year-month-day hour:minute:second (yyyy-mm-dd hh:mm:ss), and the raw data is arranged in ascending or descending order of time.

[0138] S103, this invention reads one of the following: the design power curve, the contract power curve, or the guaranteed power curve of the wind turbine, as a standard curve for correcting the measured wind speed of the measured power curve. The standard power curve data is derived from the standard wind speed... and standard power Composed of two column vectors, defined as shown in formulas 1-3:

[0139] ,1)

[0140] ,2)

[0141] ,3)

[0142] Standard wind speed vector Includes the cut-in wind speed from the wind turbine. Cut-out wind speed The standard power vector is composed of n standard center wind speed values ​​spaced at intervals of 0.5 m / s and their corresponding power values ​​according to the unit's design power curve (contract power curve, guaranteed power curve). Generally, the standard wind turbine design power curve, contract power curve, and guaranteed power curve data can all be provided in advance and directly read and applied when needed. Among them, the wind speed unit of the standard power curve is m / s, and the power unit is usually kW. After desensitization and normalization, it is a proportional value between 0 and 1.

[0143] S104 involves calculating and plotting the measured power curve of the wind turbine in the SCADA system based on the data preprocessed in S102. Generally, the statistical calculation result of the measured power curve is derived from the measured wind speed. and measured power Composed of two column vectors, as defined in formulas 4 and 5:

[0144] ,4)

[0145] ,5)

[0146] Measured wind speed n consecutive wind speed intervals are defined with an upper and lower limit of 0.25 m / s for each standard center wind speed. Based on this, the measured wind speed value within each interval is defined as the average wind speed of all 10-minute averaged segments of the original data falling within that interval. Simultaneously, the average power value corresponding to each interval is defined as the measured power value within that interval. Here, the unit for measured wind speed is m / s, and the unit for measured power is kW; after anonymization and normalization, these are also proportional values.

[0147] S105, this invention employs a method of mapping measured power to standard wind speed, correcting the measured wind speed value of the measured power curve according to the standard power curve. As shown in Formula 6, based on the measured power value of each measured power curve... Matching the standard power minimum interval of the standard power curve in which it is located The standard wind speed and standard power of the minimum interval are selected as the coordinates of the two endpoints of the corrected interpolation line segment. and The measured power value can be calculated using the linear relationship within this interval. Wind speed corrected according to the standard power curve And define the corrected wind speed vector as As shown in Formula 7:

[0148]

[0149] ,6)

[0150] ,7)

[0151] Here, i and j are any numbers between 1 and n, representing the wind speed intervals for each measured and standard power curve. When the standard power curve is complete, m can be as small as 1, indicating that the minimum standard power interval corresponds to the minimum standard wind speed interval. If the standard power curve has missing wind speed intervals, then m can be as large as n-1. Furthermore, for measured power... Power value less than the cut-in wind speed of the standard power curve Or greater than the power value corresponding to the cut-off wind speed of the standard power curve. Given that the situation has exceeded the assessment range, no correction is needed; instead, adjust the wind speed accordingly. Set to NULL.

[0152] S106, based on the measured wind speed in the wind turbine SCADA system The current wind speed transfer function has been passed. Therefore, before fitting a new wind speed transfer function, the measured wind speed must be converted. According to the current wind speed transfer function Reverse transformation to original wind speed Given the original wind speed polynomial and the measured wind speed. The functional relationship between them is defined as in Formula 8:

[0153]

[0154] ,8)

[0155] Currently, wind turbines mostly use wind speed transfer functions with a first-order linear structure, i.e., second-order and above, up to the kth-order coefficients in Equation 8. The polynomials that are all equal to 0 are used in this invention, while the wind speed transfer function used in this invention is a multi-order polynomial form, the specific order of which can be determined by training results. Therefore, given the current wind speed transfer function... Measured wind speed in SCADA system In this case, the original wind speed vector can be deduced by using the inverse function of Formula 8. The numerical values ​​are given. Here, the inverse transformation based on the first-order linear wind speed transfer function is easy to implement, while the inverse transformation of second-order and higher polynomials can be quickly implemented using the polynomial processing functions provided by Python, R, etc. The original wind speed vector after the inverse transformation is defined as shown. :

[0156] ,9)

[0157] S107, after obtaining the original wind speed corresponding to the measured wind speed of the wind turbine. and corrected wind speed Subsequently, this invention focuses on the unit operation from the cut-in wind speed. Up to rated wind speed During the initial grid connection transition phase, because the unit adopts a torque control strategy during this phase, the power output varies with wind speed, making it more suitable for applications with low initial wind speed. and corrected wind speed The function mapping relationship is fitted. As shown in Equations 9 and 10, this invention employs a polynomial curve fitting method based on least squares optimization, defining the original wind speed. and corrected wind speed Polynomial fitting mapping relationship between The new wind speed transfer function for the wind turbine has a polynomial coefficient vector B:

[0158] ,9)

[0159]

[0160] ,10)

[0161] Theoretically, the higher the order l of the polynomial is chosen, the better the new wind speed transfer function will be. The better the fit, the more accurate the result. However, to prevent overfitting and reduce unnecessary computation, this invention uses goodness-of-fit to measure the original wind speed during the grid connection transition phase of the wind turbine. Corresponding true corrected wind speed Fitted Corrected Wind Speed The goodness of fit between the two is determined using the coefficient of determination. As a statistical standard for quantifying the goodness of fit of polynomials of arbitrary order, the coefficient of determination is shown in formulas 11-13. Defined as the difference between 1 and the ratio of the sum of squared residuals (RSS) to the sum of squared mean errors (TSS). The normal range of values ​​is And the optimal value is 1, theoretically A larger value indicates a better fit. This invention specifies the coefficient of determination for fitting a polynomial of a certain order. First time greater than the decision threshold When the time is right, the higher-order polynomial fitting iteration can be stopped, and the polynomial of that order can be selected as the final fitting result of the new wind speed transfer function.

[0162] ,11)

[0163] ,12)

[0164] ,13)

[0165] yes The mean of i, where i ranges from 1 to p.

[0166] This invention, after obtaining a new wind speed transfer function for wind turbines based on data analysis from a SCADA system, also needs to evaluate the theoretical annual power generation (AEP) and the measured estimated power generation (PEP) for the current period. The degree of agreement between the measured estimated power generation and the theoretical annual power generation is used to determine whether the current wind speed transfer function needs to be replaced with the new one. The method for replacing the wind speed transfer function of a wind turbine based on a SCADA system is as follows: Figure 2 As shown:

[0167] S201, based on the standard power curve of wind turbine units, statistically calculates the theoretical annual power generation (AEP) of the units during the evaluation period.

[0168] S202, the present invention performs statistical calculations on the measured estimated power generation (PEP) of the wind turbine during the evaluation period based on the measured power curve of the wind turbine.

[0169] S203, this invention uses the ratio K (the current generation ratio) of the measured estimated power generation (PEP) to the theoretical annual power generation (AEP) to measure the conformity of the wind turbine's power generation. K is a non-negative number; when it equals 1, it indicates that the measured estimated power generation fully conforms to the theoretical annual power generation. A value greater than 1 indicates that the actual power generation capacity of the turbine is better than the theoretical design range, but this situation is almost nonexistent, and in practice, the wind speed transfer function of the turbine needs to be re-evaluated and verified. A value less than 1 indicates that the actual power generation capacity of the turbine is worse than the theoretical design range, and after excluding the influence of objective problems such as control issues, faults, and performance issues within the turbine itself, the wind speed transfer function of the turbine also needs to be re-evaluated.

[0170] S204, this invention stipulates that when the absolute value of the difference between 1 and K is greater than 5%, that is, the deviation between the unit's measured estimated power generation and the theoretical annual power generation exceeds 5% of the theoretical annual power generation, further determination is needed to determine whether the current wind speed transfer function should be calibrated. Specifically, when the difference between 1 and K is less than -5%, it indicates that the unit's measured estimated power generation exceeds the theoretical annual power generation, which is reflected in the power curve as a significant leftward shift of the measured power curve compared to the standard power curve. This situation should not occur in reality and is most likely due to abnormal operation of the wind turbine's wind measurement system or an unreasonable setting of the current wind speed transfer function. Therefore, it is necessary to further investigate the performance of the wind measurement system and replace the current wind speed transfer function with a new one. When the difference between 1 and K is greater than 5%, it indicates that the unit's measured estimated power generation is far lower than the theoretical annual power generation, which is reflected in the power curve as a significant rightward shift of the measured power curve compared to the standard power curve. This situation is relatively common and complex, and it is only meaningful to re-evaluate and calibrate the unit's wind speed transfer function after ruling out the influence of the unit itself due to unreasonable control strategies, latent faults, performance degradation, etc.

[0171] S205 After completing the optimization of the wind speed transfer function of the wind turbine based on the SCADA system, the polynomial coefficient vector B of the new transfer function can be obtained. If the conditions for transfer function replacement are met, the modification function can be enabled. Using the communication function between the field SCADA system and the wind turbine control PLC, the coefficient vector values ​​of the new wind speed transfer function are sent from the SCADA system to the PLC receiving register in order of polynomial order, and the PLC initialization wind speed transfer function coefficient values ​​are replaced, thereby realizing the dynamic replacement and agile calibration of the wind turbine wind speed transfer function.

[0172] The following example uses a wind turbine S1 of a certain model in an Inner Mongolia region of my country. Based on the SCADA system, the second-level historical operating data (i.e., measured operating data) of the unit over the past 6 months is automatically extracted, and the wind speed transfer function of the unit is evaluated. The specific steps are as follows:

[0173] Extract the raw data to be analyzed (i.e., the measured operational data) The data consists of 181 records, with a data integrity rate of approximately 98.3%, and includes a cumulative normal operating time of 3577 hours for the wind turbines connected to the grid. The data sampling frequency is 1 Hz, and the data variables include essential indicators such as wind speed, active power, generator speed, pitch angle, and operating status flags of the wind turbines.

[0174] After data cleaning, deduplication, and standardization of types and units, a total of 260,000 missing values ​​and 520,000 duplicate records were removed, achieving an actual data integrity rate of approximately 95%. Furthermore, the data types of variables such as wind speed, active power, generator speed, and pitch angle were standardized to floating-point numbers, and the data timestamp format was standardized. The original data was then sorted in ascending order by time. The units for data variables were defined as follows: wind speed: meters per second (m / s), active power: kilowatts (kW), generator speed: revolutions per minute (rpm), and pitch angle: degrees (°), thus completing the unit conversion for the original data values.

[0175] The contract power curve of the given on-site unit model is used as the standard power curve, as shown in Table 1. The standard power curve data is derived from the standard wind speed. and standard power The data consists of two column vectors. The standard wind speed is in m / s, and the standard power has been desensitized and converted to normalized values ​​between 0 and 1. The design cut-in wind speed of unit S1 is known. The cutoff wind speed is 3 m / s. The rated wind speed is 20 m / s. It is 13 m / s.

[0176] Table 1

[0177]

[0178] The measured power curve of the unit was calculated and plotted. As shown in Table 1, the measured power curve results are derived from the measured wind speed. and measured power The data consists of two column vectors, with the measured wind speed in m / s and the measured power also processed by desensitization and normalization.

[0179] The method of mapping measured power to standard wind speed is used to map the measured wind speed of the measured power curve. The corrected wind speed is obtained by processing according to the standard power curve. As shown in Table 1, the measured wind speed is corrected according to the standard power curve. An example of the mapping method is provided below. Figure 4 As shown, the wind speed in the known measured power curve Corresponding power is This power value can be mapped to the minimum power range of (0.528, 0.619] on the standard power curve, corresponding to a standard wind speed range of (8.5 m / s, 9 m / s]. Then, line segments are constructed using the start and end points of this standard power curve range as endpoints, and linear interpolation is performed using the actual power value of 0.606 to finally obtain the corrected wind speed value. .

[0180] The current wind speed transfer function used by the S1 wind turbine at the site is known. It is a first-order linear form, as shown in Equation 14, with polynomial coefficients. All coefficients of the second order and above are equal to 0, and the measured wind speed is... According to the current wind speed transfer function Reverse transformation to original wind speed As shown in Formula 15, the results are shown in Table 1, which shows the measured wind speed restored according to the current wind speed transfer function.

[0181] ,14)

[0182] ,15)

[0183] Extract the measured corrected wind speed during the grid connection transition phase of Unit S1 (corresponding to the standard wind speed range of 3m / s to 12.5m / s). And measured wind speed Using a new wind speed transfer function Starting from order 1, polynomial fitting is performed by progressively increasing the order until the coefficient of determination of the fitting at a certain order is obtained. First time greater than the decision threshold So far, the fitting iteration results are shown in Table 2. A fourth-order polynomial can be selected as the new wind speed transfer function. The fitting results are as follows Figure 5 As shown.

[0184] Table 2

[0185]

[0186] Based on the standard power curve and measured power curve of wind turbine units, the theoretical annual power generation (AEP) and the measured estimated power generation (PEP) of the units during the assessment period were statistically analyzed, and the conformity coefficient of the ratio of the measured estimated power generation to the theoretical annual power generation was calculated. The net difference from 1 is -21.43%, and the absolute difference significantly exceeds 5%, indicating that the actual estimated power generation of the unit significantly exceeds the theoretical annual power generation. Figure 4 As shown in the figure, the measured power curve is significantly shifted to the left compared to the standard power curve, indicating that the performance of the wind measurement system needs to be further investigated and the current wind speed transfer function needs to be replaced.

[0187] Finally, utilizing the communication function between the on-site SCADA system and the wind turbine control PLC, the parameter vector of the new wind speed transfer function is... The wind speed transfer function is sent from the SCADA system to the PLC receiving register in ascending order of order, replacing the coefficient values ​​of the current wind speed transfer function in the PLC main control logic, thereby realizing dynamic evaluation, replacement and agile calibration of the wind turbine's wind speed transfer function.

[0188] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this disclosure.

[0189] The above is an introduction to the method embodiments. The following describes the solution described in this disclosure further through device embodiments.

[0190] Figure 6 A block diagram of a wind turbine wind speed transfer function optimization device 600 based on a SCADA system according to an embodiment of the present disclosure is shown. Figure 6 As shown, the device 600 includes:

[0191] The first acquisition module 610 is used to acquire the standard power curve of the wind turbine, wherein the standard power curve is used to characterize the correspondence between standard power and standard wind speed.

[0192] The plotting module 620 is used to plot the measured power curve of the wind turbine based on the measured operating data of the wind turbine, wherein the measured power curve is used to show the correspondence between the measured power and the measured wind speed.

[0193] The correction module 630 is used to correct the measured wind speed corresponding to the measured power on the measured power curve according to the standard power curve, so as to obtain the corrected wind speed.

[0194] The restoration module 640 is used to restore the measured wind speed according to the current wind speed transfer function to obtain the original wind speed;

[0195] The second acquisition module 650 is used to acquire a new wind speed transfer function based on the corrected wind speed and the original wind speed.

[0196] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the described module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0197] According to embodiments of the present disclosure, the present disclosure also provides an electronic device and a non-transitory computer-readable storage medium storing computer instructions.

[0198] Figure 7 A schematic block diagram of an electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0199] Device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0200] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0201] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as method 300. For example, in some embodiments, method 300 may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of method 300 described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform method 300 by any other suitable means (e.g., by means of firmware).

[0202] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0203] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0204] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0205] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0206] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0207] Computing systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0208] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0209] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for optimizing the wind speed transfer function of a wind turbine based on a SCADA system, characterized in that, include: Obtain the standard power curve of the wind turbine, wherein the standard power curve is used to characterize the correspondence between standard power and standard wind speed; Based on the measured operating data of the wind turbine, the measured power curve of the wind turbine is plotted, wherein the measured power curve is used to show the correspondence between measured power and measured wind speed. Based on the standard power curve, the measured wind speed corresponding to the measured power on the measured power curve is corrected to obtain the corrected wind speed. The measured wind speed is reconstructed based on the current wind speed transfer function to obtain the original wind speed; Based on the corrected wind speed and the original wind speed, a new wind speed transfer function is obtained; wherein, the new wind speed transfer function includes a wind speed transfer function in the form of a multi-order polynomial. The step of correcting the measured wind speed corresponding to the measured power on the measured power curve according to the standard power curve to obtain the corrected wind speed includes: Based on the measured power on the measured power curve, match the minimum standard power range of the standard power curve in which it is located; Determine the minimum standard wind speed range on the standard power curve that corresponds to the minimum standard power range; The endpoint coordinates of the minimum standard power range and the endpoint coordinates of the minimum standard wind speed range are calculated using a preset interpolation method to obtain the corrected wind speed.

2. The method as described in claim 1, characterized in that, The step of restoring the measured wind speed to the original wind speed based on the current wind speed transfer function includes: The measured wind speed is transformed in reverse according to the current wind speed transfer function to obtain the original wind speed.

3. The method as described in claim 1, characterized in that, The step of obtaining a new wind speed transfer function based on the corrected wind speed and the original wind speed includes: The corrected wind speed and the original wind speed are subjected to polynomial iterative fitting, and the coefficient of determination of each iterative fitting is obtained; Obtain the preset iteration threshold; The coefficient of determination of each iteration is compared with the preset iteration threshold. When the coefficient of determination is greater than the preset iteration threshold for the first time, the iterative fitting stops, and the polynomial at which the iterative fitting stops is taken as the new wind speed transfer function.

4. The method as described in claim 1, characterized in that, The step of plotting the measured power curve of the wind turbine based on the measured operating data of the wind turbine includes: Delete the missing data from the measured operating data of the wind turbine; After deletion, the remaining measured operating data of the wind turbine will be sorted according to timestamps. The first record of all duplicate data is retained sequentially to obtain the deduplicated test data. The deduplicated measured operational data is then standardized in terms of type and unit. Based on the standardized measured operating data, the measured power curve of the wind turbine was plotted.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: Calculate the theoretical power generation of the wind turbine based on the standard power curve; Based on the measured power curve, calculate the measured estimated power generation of the wind turbine. Based on the theoretical power generation and the measured estimated power generation, determine whether to use the new wind speed transfer function to replace the current wind speed transfer function.

6. The method as described in claim 5, characterized in that, The step of determining whether to use the new wind speed transfer function to replace the current wind speed transfer function based on the theoretical power generation and the measured estimated power generation includes: Calculate the current power generation ratio of the measured estimated power generation to the theoretical power generation; Obtain the threshold for the proportion of power generation; Calculate the absolute value of the difference between the current power generation ratio and 1; If the absolute value of the difference is greater than the power generation ratio threshold, then it is determined that the new wind speed transfer function will be used to replace the current wind speed transfer function.

7. An optimization device for the wind speed transfer function of a wind turbine based on a SCADA system, characterized in that, include: The first acquisition module is used to acquire the standard power curve of the wind turbine, wherein the standard power curve is used to characterize the correspondence between standard power and standard wind speed; The plotting module is used to plot the measured power curve of the wind turbine based on the measured operating data of the wind turbine, wherein the measured power curve is used to show the correspondence between the measured power and the measured wind speed. The correction module is used to correct the measured wind speed corresponding to the measured power on the measured power curve according to the standard power curve, so as to obtain the corrected wind speed. The restoration module is used to restore the measured wind speed according to the current wind speed transfer function to obtain the original wind speed; The second acquisition module is used to acquire a new wind speed transfer function based on the corrected wind speed and the original wind speed; wherein the new wind speed transfer function includes a wind speed transfer function in the form of a multi-order polynomial. The correction module is specifically used for: Based on the measured power on the measured power curve, match the minimum standard power range of the standard power curve in which it is located; Determine the minimum standard wind speed range on the standard power curve that corresponds to the minimum standard power range; The endpoint coordinates of the minimum standard power range and the endpoint coordinates of the minimum standard wind speed range are calculated using a preset interpolation method to obtain the corrected wind speed.

8. An electronic device, characterized in that, include: Memory and processor The memory stores a computer program, and when the processor executes the program, it implements the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor corresponding to the electronic device, the electronic device is able to implement the optimization method of the wind speed transfer function of the wind turbine based on the SCADA system as described in any one of claims 1-6.

Images