A method and device for processing operating variable data of a wind turbine

Abstract

The present application provides a method and apparatus for processing operational variable data of a wind turbine, relating to the field of data processing technology, and aiming to eliminate the influence of environmental variable data on operational variable data. The method comprises: obtaining environmental variable data and operational variable data of the wind turbine, wherein the operational variable data is data influenced by the environmental variable data; constructing a regression model that characterizes the correlation between the environmental variable data and the operational variable data; solving the regression model to obtain a solution to the regression model; and adjusting the operational variable data based on the solution to obtain operational variable data that is not influenced by the environmental variable data.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for processing operating variable data of a wind turbine. Background Art

[0002] Wind power generation is beneficial for addressing the increasingly severe energy crisis and environmental issues. Wind turbines are key equipment for wind power generation. Real-time monitoring of wind turbine operating status can provide a reference for developing wind farm operation plans and facilitate condition-based maintenance of wind turbines, avoiding economic losses caused by excessive or untimely maintenance and ensuring the reliability of wind power generation.

[0003] Supervisory control and data acquisition (SCADA) systems are widely used in modern wind turbines. They can collect relevant data during the service life of wind turbines through various sensors and transmit it to the central control computer through the network. The data includes data on environmental variables such as wind speed, wind direction, and ambient temperature, as well as data on operating variables such as speed, power generation, and bearing temperature. The operating variable data in the wind turbine data collected by SCADA is expected to characterize the operating status of the wind turbine, reflect the service status of different components in the power generation process, and create conditions for status monitoring and fault diagnosis.

[0004] However, wind turbines are in a complex and changeable environment, and the wind loads they are subjected to have time-varying characteristics. The operating status of wind turbines is also changeable with changes in the environment, which will interfere with the operating variable data and make it impossible to accurately reflect the actual service status of the wind turbines. This brings difficulties to the operating status assessment of wind turbines. The impact of environmental factors on operating variables has become an obstacle to the implementation of condition-based maintenance and intelligent operation and maintenance of wind turbines. Summary of the Invention

[0005] In view of the above problems, embodiments of the present invention provide a method and apparatus for processing operating variable data of a wind turbine, so as to overcome the above problems or at least partially solve the above problems.

[0006] A first aspect of an embodiment of the present invention provides a method for processing operating variable data of a wind turbine, comprising:

[0007] Acquiring environmental variable data and operating variable data of the wind turbine, wherein the operating variable data is data affected by the environmental variable data;

[0008] Constructing a regression model that characterizes the correlation between the environmental variable data and the operational variable data;

[0009] solving the regression model to obtain a solution of the regression model;

[0010] According to the solution, the operating variable data is adjusted to obtain operating variable data that is not affected by the environmental variable data.

[0011] Optionally, the constructing of a regression model characterizing the correlation between the environmental variable data and the operational variable data includes:

[0012] The correlation between the environmental variable data and the operational variable data is modeled using a cubic spline function to obtain the regression model.

[0013] Optionally, solving the regression model includes:

[0014] Taking the basis function coefficients of the cubic spline function as optimization variables, constructing a variable regression optimization problem under smoothing regularization constraints;

[0015] The basis function coefficients in the variable regression optimization problem under the smoothing regularization constraint are solved.

[0016] Optionally, solving the basis function coefficients in the variable regression optimization problem under the smoothing regularization constraint includes:

[0017] Discretizing the variable regression optimization problem under the smooth regularization constraint to obtain the variable regression optimization problem under discrete conditions;

[0018] The basis function coefficients in the variable regression optimization problem under the discrete conditions are solved.

[0019] Optionally, obtaining environmental variable data and operating variable data of the wind turbine includes:

[0020] Performing normalization processing on the environmental variable data to obtain the environmental variable data that eliminates the influence of absolute amplitude differences of different environmental variable data;

[0021] Normal standardization processing is performed on the operating variable data to obtain the operating variable data that eliminates the influence of the absolute amplitude difference of different operating variable data.

[0022] Optionally, after obtaining the operating variable data not affected by the environmental variable data, the method further includes:

[0023] The state of the wind turbine is monitored using the operating variable data that is not affected by the environmental variable data.

[0024] Optionally, after obtaining the operating variable data not affected by the environmental variable data, the method further includes:

[0025] Fault diagnosis of the wind turbine is performed using the operating variable data that is not affected by the environmental variable data.

[0026] A second aspect of an embodiment of the present invention provides a device for processing operating variable data of a wind turbine, comprising:

[0027] A data acquisition module, configured to acquire environmental variable data and operating variable data of the wind turbine, wherein the operating variable data is data affected by the environmental variable data;

[0028] A model building module, used to build a regression model that characterizes the correlation between the environmental variable data and the operating variable data;

[0029] A model solving module, used to solve the regression model to obtain a solution of the regression model;

[0030] A data adjustment module is used to adjust the operating variable data according to the solution to obtain operating variable data that is not affected by the environmental variable data.

[0031] Optionally, after obtaining the operating variable data not affected by the environmental variable data, the method further includes:

[0032] The state monitoring module is used to monitor the state of the wind turbine using the operating variable data that is not affected by the environmental variable data.

[0033] Optionally, after obtaining the operating variable data not affected by the environmental variable data, the method further includes:

[0034] The fault diagnosis module is used to perform fault diagnosis on the wind turbine using the operating variable data that is not affected by the environmental variable data.

[0035] The embodiments of the present invention include the following advantages:

[0036] In this embodiment, a regression model is constructed to characterize the correlation between environmental variable data and operational variable data. The correlation between the environmental variable data and the operational variable data can be obtained based on the solution of the regression model. Therefore, the solution of the regression model can be used to adjust the operational variable data, removing changes caused by the correlation, thereby obtaining operational variable data unaffected by the environmental variable data. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0038] Figure 1 is a flowchart of a method for processing operating variable data of a wind turbine according to an embodiment of the present invention;

[0039] Figure 2 It is a schematic diagram of multiple environmental variable data after standardization;

[0040] Figure 3 It is a schematic diagram of the normalized operating variable data;

[0041] Figure 4 is a schematic diagram of adjusted operating variable data in an embodiment of the present invention;

[0042] Figure 5 It is a schematic diagram of the correlation between the operational variable data and the environmental variable data before and after processing;

[0043] Figure 6 It is a structural diagram of a device for processing operating variable data of a wind turbine according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0045] Reference Figure 1 FIG. 1 is a flowchart showing the steps of processing the operating variable data of a wind turbine according to an embodiment of the present invention, as shown in FIG. Figure 1 As shown, the method for processing the operating variable data of the wind turbine may specifically include the following steps:

[0046] Step S11: Acquire environmental variable data and operating variable data of the wind turbine, where the operating variable data is data affected by the environmental variable data.

[0047] The SCADA system can collect a variety of data from wind turbines through various sensors. From this data, it can derive I environmental variable data describing the wind turbine's operating environment, such as wind speed, wind direction, and ambient temperature. From this data, it can also derive J operational variable data describing the wind turbine's operating status, such as speed, generated power, and lubricating oil temperature.

[0048] Because the absolute amplitudes of various data may vary—for example, one type of data may have an absolute amplitude ranging from 0 to 10, while another may have an absolute amplitude ranging from 0 to 1000—it is necessary to eliminate the influence of these differences in absolute amplitude. To eliminate this influence, normalization can be performed on each type of data to convert the data to the same standard.

[0049] The running variable data can be normalized by the following formula:

[0050]

[0051] Among them, x i is the i-th running variable data after normal standardization processing, is the i-th running variable data without normal standardization processing, (i=1,2,…,I), mean() represents the mean, and std() represents the standard deviation.

[0052] The environmental variable data can be normalized using the following formula:

[0053]

[0054] Among them, y j is the jth running variable data after normal standardization processing, is the j-th running variable data without normal standardization processing, (j=1,2,…,J), mean() represents the mean, and std() represents the standard deviation.

[0055] Optionally, other standardization processing may be performed on the environmental variable data and the operating variable data to eliminate the influence of the absolute amplitude difference of different data.

[0056] Step S12: constructing a regression model that characterizes the correlation between the environmental variable data and the operating variable data.

[0057] A regression model is constructed using the environmental variable data and the operating variable data, and the regression model reflects the correlation between the environmental variable data and the operating variable data.

[0058] Step S13: solving the regression model to obtain a solution of the regression model.

[0059] Step S14: adjusting the operating variable data according to the solution to obtain operating variable data that is not affected by the environmental variable data.

[0060] Because the regression model reflects the correlation between environmental variable data and operating variable data, the solution of the regression model can reflect the correlation between environmental variable data and operating variable data. The solution of the regression model can then be used to adjust the operating variable data, remove changes caused by the correlation from the operating variable data, and thus obtain operating variable data that is not affected by the environmental variable data.

[0061] Using the technical solutions of the embodiments of this application, a regression model is constructed to characterize the correlation between environmental variable data and operational variable data. Based on the solution of the regression model, the correlation between the environmental variable data and the operational variable data can be obtained. Therefore, the solution of the regression model can be used to adjust the operational variable data, removing changes caused by the correlation, thereby obtaining operational variable data that is unaffected by the environmental variable data.

[0062] Optionally, based on the above technical solution, the regression model constructed can be constructed using a cubic spline function. The constructed regression model can be expressed by the following formula:

[0063]

[0064] in, It is the operating variable data affected by the environmental variable data, t is the sampling time point, t=1,2,…,T, T is the number of sampling time points, g j,k is the basis function of the cubic spline function, c i,j,k are basis function coefficients.

[0065] g j,1 (x)=1,g j,2 (x)=x,g j,3 (x) = h j,1 (x)–h j,T-1 (x),…,g j,T (x) = h j,T-2 (x)–h j,T-1 (x). Where:

[0066]

[0067] Among them, (x) + =max{0,x} is a positive function.

[0068] Optionally, based on the above technical solution, because the cubic spline function is intended to fit the correlation between the environmental variable data and the operating variable data, and the cubic spline function has smoothness, it is necessary to perform smooth regularization constraints on the cubic spline function.

[0069] The basis function coefficient c of the cubic spline function can be i,j,k To optimize the variables, we construct a variable regression optimization problem under smooth regularization constraints:

[0070]

[0071] Among them, λ>0, λ is the regularization parameter, and its value reflects the weight of the smoothing regularization constraint in the process of solving the optimization problem. Generally, the empirical value of λ is 0.5.

[0072] Therefore, solving the regression model can be converted into solving the basis function coefficients in the variable regression optimization problem under smooth regularization constraints.

[0073] Optionally, based on the above technical solution, because the sampled data of the wind turbine is discrete and the cubic spline function is continuous, the regression model needs to be discretized.

[0074] The variable regression optimization problem under smooth regularization constraints can be discretized to obtain the variable regression optimization problem under discrete conditions. In order to concisely represent the variable regression optimization problem under discrete conditions, multiple operators can be defined.

[0075] Mixed integrals can be defined:

[0076] Create a running variable vector: x i =[x i (1),x i (2),…,x i (T)] T

[0077] Create coefficient vector: c i =[c i,1,1 ,c i,1,2 ,…,c i,1,T ,c i,2,1 ,…,c i,J,T ] T

[0078] Create the basis matrix:

[0079] Create the differentiation matrix:

[0080] The meaning of each character can be found in the previous text.

[0081] By defining the above operators, we can obtain the variable regression optimization problem under discrete conditions represented by the following formula:

[0082]

[0083] The meaning of each character can be found in the previous text.

[0084] By making the differential of your objective function containing the optimization variable zero, you can solve the variable regression optimization problem under discrete conditions:

[0085]

[0086] According to the basis function coefficients, the running variable data Make adjustments to eliminate the impact of factors related to environmental changes:

[0087]

[0088] in, It is the running variable data that is not affected by the environment variable data.

[0089] Alternatively, based on the above technical solution, the operational variable data unaffected by the environmental variable data can accurately reflect the actual service status of the wind turbine. Therefore, after obtaining the operational variable data unaffected by the environmental variable data, the operational variable data unaffected by the environmental variable data can be used to perform status detection and / or fault diagnosis on the wind turbine.

[0090] Compared with using operating variable data affected by environmental variable data to perform status detection and / or fault diagnosis on wind turbines, the results obtained by using operating variable data not affected by environmental variable data to perform status detection and / or fault diagnosis on wind turbines are more accurate.

[0091] The SCADA data of wind turbines were collected in a certain wind farm, which included I = 3 environmental variable data - wind speed, wind direction, ambient temperature, and J = 22 operating variable data - generator speed, grid side active power, yaw position, yaw speed, blade pitch angle 1, blade 2 pitch angle 3, blade pitch speed, blade pitch speed 2, blade pitch speed 3, pitch motor temperature, pitch motor temperature, pitch motor temperature, acceleration direction, acceleration in the y direction, ambient temperature, engine compartment temperature, ng5 temperature 1, ng5 temperature 2, ng5 temperature 3, ng5 charger current 1, ng5 charger current 2.

[0092] Figure 2 A schematic diagram showing multiple environmental variable data after standardization processing, Figure 3Figure 2 shows a schematic diagram of normalized operating variable data. It can be seen that, regardless of whether the wind turbine is in a healthy or faulty state, environmental variables such as wind speed, wind direction, and ambient temperature exhibit significant time-varying characteristics. This results in the wind turbine's operating status being affected by changes in environmental factors, resulting in the operational variable data being highly variable and therefore difficult to directly reflect the wind turbine's operating status. Figure 3 The average variance of the running variable data shown is 0.2116, and the average variance reflects the volatility of the data.

[0093] Figure 4 FIG. 1 shows a schematic diagram of the adjusted operating variable data. The operating variable data obtained after adjusting the operating variable data using the method for processing the operating variable data of the wind turbine according to the embodiment of the present application is as follows: Figure 4 As shown in Figure 2, the average variance is reduced to 0.0068, so its volatility is relatively Figure 3 It becomes smaller, which reflects that the technical solution of the present invention can reduce the variability of operating variable data due to environmental changes, thereby providing a more reliable reference for tasks such as wind turbine status monitoring and fault diagnosis.

[0094] The maximum information coefficient was used to characterize the correlation between the operational variable data and the environmental variable data. The results are as follows: Figure 5 The schematic diagram of the correlation between the operating variable data and the environmental variable data before and after processing shows that after the operating variable data is adjusted by the technical solution of the embodiment of the present application, the correlation between the operating variable data and the environmental variable data is significantly reduced, which further illustrates that the present invention can reduce the impact of changes in environmental factors on the operating variable data, so that the operating variable data can be used to more accurately reflect the operating status of the wind turbine, thereby creating favorable conditions for subsequent tasks such as status monitoring and operation control.

[0095] It should be noted that for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0096] Figure 6 FIG. 1 is a schematic structural diagram of a device for processing operating variable data of a wind turbine according to an embodiment of the present invention. Figure 6 As shown, a device for processing operating variable data of a wind turbine includes a data acquisition module, a model building module, a model solving module and a data adjustment module, wherein:

[0097] A data acquisition module, configured to acquire environmental variable data and operating variable data of the wind turbine, wherein the operating variable data is data affected by the environmental variable data;

[0098] A model building module, used to build a regression model that characterizes the correlation between the environmental variable data and the operating variable data;

[0099] A model solving module, used to solve the regression model to obtain a solution of the regression model;

[0100] A data adjustment module is used to adjust the operating variable data according to the solution to obtain operating variable data that is not affected by the environmental variable data.

[0101] Optionally, the model building module includes:

[0102] The model building submodule is used to use a cubic spline function to model the correlation between the environmental variable data and the operating variable data to obtain the regression model.

[0103] Optionally, the model solving module includes:

[0104] A smoothing submodule, configured to construct a variable regression optimization problem under a smoothing regularization constraint using the basis function coefficients of the cubic spline function as optimization variables;

[0105] The solution submodule is used to solve the basis function coefficients in the variable regression optimization problem under the smooth regularization constraint.

[0106] Optionally, the solution submodule includes:

[0107] A discrete unit is used to discretize the variable regression optimization problem under the smooth regularization constraint to obtain the variable regression optimization problem under discrete conditions;

[0108] A solving unit is used to solve the basis function coefficients in the variable regression optimization problem under the discrete conditions.

[0109] Optionally, the data acquisition module includes:

[0110] A first processing submodule is configured to perform normalization processing on the environmental variable data to obtain the environmental variable data that eliminates the influence of absolute amplitude differences between different environmental variable data;

[0111] The second processing submodule is configured to perform normal standardization processing on the operating variable data to obtain the operating variable data that eliminates the influence of the absolute amplitude difference of different operating variable data.

[0112] Optionally, after obtaining the operating variable data not affected by the environmental variable data, the method further includes:

[0113] The state monitoring module is used to monitor the state of the wind turbine using the operating variable data that is not affected by the environmental variable data.

[0114] Optionally, after obtaining the operating variable data not affected by the environmental variable data, the method further includes:

[0115] The fault diagnosis module is used to perform fault diagnosis on the wind turbine using the operating variable data that is not affected by the environmental variable data.

[0116] It should be noted that the device embodiment is similar to the method embodiment, so the description is relatively simple, and the relevant parts can be referred to the method embodiment.

[0117] An embodiment of the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for processing operating variable data of a wind turbine disclosed in an embodiment of the present application is implemented.

[0118] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed, the method for processing operating variable data of a wind turbine disclosed in an embodiment of the present application is implemented.

[0119] An embodiment of the present invention further provides a computer program product, including a computer program or computer instructions, which, when executed by a processor, implements the method for processing operating variable data of a wind turbine as disclosed in the embodiment of the present application.

[0120] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0121] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, embodiments of the present invention may take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0122] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, apparatuses, electronic devices, and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0123] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0124] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0125] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0126] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only 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. Moreover, the terms "comprises," "includes," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements that are inherent to such process, method, article, or terminal device. In the absence of further restrictions, an element defined by the phrase "comprises a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0127] The above is a detailed introduction to the method and device for processing operating variable data of a wind turbine provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for processing operating variable data of a wind turbine, characterized in that: include: Acquiring environmental variable data and operating variable data of the wind turbine, and performing normalization processing on the environmental variable data and the operating variable data to obtain the environmental variable data and the operating variable data that eliminate the influence of absolute amplitude differences between different environmental variable data and operating variable data; The operating variable data is data affected by the environmental variable data; The environmental variable data include: wind speed, wind direction and ambient temperature; the operating variable data include: rotation speed, power generation and lubricating oil temperature; Constructing a regression model to characterize the correlation between the environmental variable data after normalization processing and the operational variable data after normalization processing; solving the regression model to obtain a solution of the regression model; adjusting the operating variable data according to the solution to obtain operating variable data that is not affected by the environmental variable data; The constructed regression model is expressed by the following formula: ； in, is the operating variable data affected by the environmental variable data, t is the sampling time point, t = 1, 2, …, T, T is the number of sampling time points; y j is the jth environmental variable data after normal standardization, j = 1, 2, ..., J; g j, k is the basis function of the cubic spline function, is the basis function coefficient; the expression of the basis function of the cubic spline function is: , , , …, ,in: ;(x) + = max{0, x} is a positive function; The basis function coefficients of the cubic spline function To optimize the variables, we construct a variable regression optimization problem under smooth regularization constraints: ； Among them, λ is 0.5, λ is the regularization parameter, and its value reflects the weight of the smooth regularization constraint in the process of solving the optimization problem; x i is the i-th running variable data after normal standardization; Solving the regression model is converted into solving the basis function coefficients in the variable regression optimization problem under smooth regularization constraints; Discretize the regression model: Define the mixed integral: ; Create a running variable vector: x i = [x i (1), x i (2), …, x i (T)] T ; where x i is the running variable data vector, x i (T) is the operating variable data at the sampling time point T; Create coefficient vector: c i = [c i, 1, 1 , c i, 1, 2 ,…, c i, 1, T ,c i, 2, 1 , …, c i, J, T ] T ; Among them, c i is the basis function coefficient vector, c i, J, T is the basis function coefficient of the J-th environmental variable data at the sampling time point T; Create the basis matrix: ； Create the differentiation matrix: ； Through the operators defined above, the variable regression optimization problem under discrete conditions is obtained as represented by the following formula: ; Solve the variable regression optimization problem under discrete conditions by setting the differential of the objective function containing the optimization variable to zero: ； According to the basis function coefficients, the running variable data Make adjustments to eliminate the impact of factors related to environmental changes: ;in, It is the running variable data that is not affected by the environment variable data.

2. The method according to claim 1, characterized in that After obtaining the operational variable data that is not affected by the environmental variable data, the method further includes: The state of the wind turbine is monitored using the operating variable data that is not affected by the environmental variable data.

3. The method according to claim 1, characterized in that After obtaining the operational variable data that is not affected by the environmental variable data, the method further includes: Fault diagnosis of the wind turbine is performed using the operating variable data that is not affected by the environmental variable data.

4. A device for processing operating variable data of a wind turbine, characterized in that: include: a data acquisition module, configured to acquire environmental variable data and operating variable data of the wind turbine, and perform normalization processing on the environmental variable data and the operating variable data to obtain the environmental variable data and the operating variable data in which the influence of the absolute amplitude difference between different environmental variable data and operating variable data is eliminated; The operating variable data is data affected by the environmental variable data; The environmental variable data include: wind speed, wind direction and ambient temperature; the operating variable data include: rotation speed, power generation and lubricating oil temperature; A model building module is used to build a regression model that represents the correlation between the environmental variable data after normal standardization and the operating variable data after normal standardization; A model solving module, used to solve the regression model to obtain a solution of the regression model; a data adjustment module, configured to adjust the operating variable data according to the solution to obtain operating variable data that is not affected by the environmental variable data; The model building module is specifically used to build a regression model represented by the following formula: ； in, is the operating variable data affected by the environmental variable data, t is the sampling time point, t = 1, 2, …, T, T is the number of sampling time points; y j is the jth environmental variable data after normal standardization, j = 1, 2, ..., J; g j, k is the basis function of the cubic spline function, is the basis function coefficient; the expression of the basis function of the cubic spline function is: , , , …, ,in: ;(x) + = max{0, x} is a positive function; The model solving module is specifically used for: The basis function coefficients of the cubic spline function To optimize the variables, we construct a variable regression optimization problem under smooth regularization constraints: ； Among them, λ is 0.5, λ is the regularization parameter, and its value reflects the weight of the smooth regularization constraint in the process of solving the optimization problem; x i is the i-th running variable data after normal standardization; Solving the regression model is converted into solving the basis function coefficients in the variable regression optimization problem under smooth regularization constraints; Discretize the regression model: Define the mixed integral: ; Create a running variable vector: x i = [x i (1), x i (2), …, x i (T)] T ; where x i is the running variable data vector, x i (T) is the operating variable data at sampling time T; Create coefficient vector: c i = [c i, 1, 1 , c i, 1, 2 ,…, c i, 1, T ,c i, 2, 1 , …, c i, J, T ] T ; Among them, c i is the basis function coefficient vector, c i, J, T is the basis function coefficient of the J-th environmental variable data at the sampling time point T; Create the basis matrix: ； Create the differentiation matrix: ； Through the operators defined above, the variable regression optimization problem under discrete conditions is obtained as represented by the following formula: ; Solve the variable regression optimization problem under discrete conditions by setting the differential of the objective function containing the optimization variable to zero: ； The data adjustment module is specifically used to: adjust the running variable data according to the basis function coefficients Make adjustments to eliminate the impact of factors related to environmental changes: ;in, It is the running variable data that is not affected by the environment variable data.

5. The device according to claim 4, characterized in that After obtaining the operational variable data that is not affected by the environmental variable data, the method further includes: The state monitoring module is used to monitor the state of the wind turbine using the operating variable data that is not affected by the environmental variable data.

6. The device according to claim 4, characterized in that After obtaining the operational variable data that is not affected by the environmental variable data, the method further includes: The fault diagnosis module is used to perform fault diagnosis on the wind turbine using the operating variable data that is not affected by the environmental variable data.

Images