Correction method and device for wind turbine load estimator and wind turbine generator set

Abstract

The application provides a wind turbine load estimator correction method, device and wind turbine, and belongs to the field of wind power generation. The method comprises the following steps: obtaining first wind turbine operating parameters and first load parameters of a wind power generator under a target working condition to obtain a load estimator, wherein the load estimator comprises a first conversion matrix set corresponding to multiple working points, and the working points are determined based on the rotating speed and torque of the wind turbine; obtaining second wind turbine operating parameters and second load parameters of the wind power generator under an actual working condition, obtaining a second conversion matrix set after filtering estimation based on a pre-adjusted filter; and correcting the first conversion matrix set according to the second conversion matrix set to complete the correction of the wind turbine load estimator. The application corrects the parameters of the load estimator under the target working condition by using the operating parameters and load measurement parameters under the actual working condition, improves the accuracy of the load estimator, and solves the defect that the actual application of the load estimator is limited.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and in particular to a correction method and device for a wind turbine load estimator and a wind turbine generator set. Background Art

[0002] The load of a wind turbine is closely related to its safety. The load estimator is used to achieve long-term monitoring of the load of a wind turbine.

[0003] The existing load estimator is established based on a data-driven approach. It uses simulation data to train a computational model between load and actual measurable data. The trained load estimator is embedded in the controller program to achieve high-frequency load estimation.

[0004] However, due to differences in geographical location and performance degradation among wind turbines, there are certain differences between the data obtained from simulation and the actual operating conditions, resulting in insufficient accuracy of the trained load estimator and limiting its practical application. Summary of the Invention

[0005] The present invention provides a correction method and device for a wind turbine load estimator and a wind turbine generator set, which are used to solve the defects in the prior art that due to differences in geographical location and performance degradation of each wind turbine, the data obtained by simulation are different from the actual working conditions, resulting in insufficient accuracy of the trained load estimator and limited practical application of the load estimator.

[0006] In a first aspect, the present invention provides a method for correcting a wind turbine load estimator, comprising: obtaining a first wind turbine operating parameter and a first load parameter of a wind turbine under a target operating condition to obtain a load estimator, wherein the load estimator includes a first conversion matrix set corresponding to multiple operating points, and the operating point is determined based on the speed and torque of the wind turbine; obtaining a second wind turbine operating parameter and a second load parameter of the wind turbine under actual operating conditions, and obtaining a second conversion matrix set after filtering estimation based on a pre-adjusted filter; and correcting the first conversion matrix set based on the second conversion matrix set to complete the correction of the wind turbine load estimator.

[0007] According to a correction method for a wind turbine load estimator provided by the present invention, the correction of the first conversion matrix set based on the second conversion matrix set includes: correcting the first conversion matrix in the first conversion matrix set based on a proportional scaling method according to the second conversion matrix set, thereby completing the correction of the first conversion matrix set.

[0008] According to a correction method for a wind turbine load estimator provided by the present invention, the first conversion matrix in the first conversion matrix set is corrected based on the proportional scaling method according to the second conversion matrix, including: determining the difference in conversion coefficients of the target parameters in the second conversion matrix and the first conversion matrix; determining the first distance between the conversion coefficient of the target parameter in the first conversion matrix and each normalized working point; and correcting the conversion coefficient of each parameter in the first conversion matrix in turn according to the first distance, the preset second distance and the difference in conversion coefficient to complete the correction of the first conversion matrix, wherein the second distance is determined based on the first distance.

[0009] According to a correction method for a wind turbine load estimator provided by the present invention, the first wind turbine operating parameter and the first load parameter of the wind turbine under the target operating condition are obtained to obtain the load estimator, including: obtaining the first wind turbine operating parameter and the first load parameter of the wind turbine under the target operating condition based on simulation software; and determining a first conversion matrix set between the first wind turbine operating parameter and the first load parameter based on a regression analysis method to obtain the load estimator.

[0010] According to a correction method for a fan load estimator provided by the present invention, the first conversion matrix set between the first fan operating parameter and the first load parameter is determined based on the regression analysis method, including: decomposing the first fan operating parameter to obtain the high-frequency components of the first fan operating parameter and the low-frequency components of the first fan operating parameter corresponding to the multiple working points; obtaining the conversion matrix between the high-frequency components of the first fan operating parameter and the first load parameter and the conversion matrix between the low-frequency components of the first fan operating parameter and the first load parameter based on the regression analysis method to obtain the first conversion matrix set.

[0011] According to a correction method for a wind turbine load estimator provided by the present invention, the second conversion matrix set after filtering estimation is obtained based on the pre-adjusted filter, including: obtaining the Kalman filter state equation and the Kalman filter observation equation at the target moment according to the second wind turbine operating parameter, the second load parameter and the first conversion matrix set; determining the conversion matrix prediction value and the error covariance; determining the Kalman gain according to the error covariance; and obtaining the second conversion matrix and the error covariance estimate according to the conversion matrix prediction value and the Kalman gain.

[0012] According to the method for modifying the wind turbine load estimator provided by the application, the Kalman filtering state equation at the target moment is obtained according to the first conversion matrix set, and the Kalman filtering observation equation at the target moment is obtained according to the second wind turbine operation parameter, the second load parameter and the first conversion matrix set.

[0013] According to the method for modifying the wind turbine load estimator provided by the application, the Kalman gain is determined according to the error covariance, and the method comprises the following steps of: determining the Kalman gain according to the error covariance and the second load parameter.

[0014] According to the method for modifying the wind turbine load estimator provided by the application, the second conversion matrix and the error covariance estimation value are obtained according to the conversion matrix prediction value and the Kalman gain, and the method comprises the following steps of: obtaining the second conversion matrix according to the conversion matrix prediction value, the Kalman gain, the second wind turbine operation parameter and the second load parameter; and obtaining the error covariance estimation value according to the Kalman gain, the second load parameter and the error covariance.

[0015] In the second aspect, the application provides a device for modifying a wind turbine load estimator, which comprises: a model determination module, which is used to obtain the first wind turbine operation parameter and the first load parameter of a wind turbine under a target working condition, and obtain a load estimator, wherein the load estimator comprises a first conversion matrix set corresponding to a plurality of working points, and the working points are determined based on the rotational speed and the torque of the wind turbine; a matrix determination module, which is used to obtain the second wind turbine operation parameter and the second load parameter of the wind turbine under an actual working condition, and obtain a second conversion matrix set after filtering based on a pre-adjusted filter; and a parameter modification module, which is used to modify the first conversion matrix set according to the second conversion matrix set, so as to complete the modification of the wind turbine load estimator.

[0016] In the third aspect, the application further provides a wind turbine, which comprises a wind turbine body, a wind turbine load estimator modification processor arranged in the wind turbine body, a memory, and a program or instruction stored in the memory and capable of running on the wind turbine load estimator modification processor, and the program or instruction is executed by the wind turbine load estimator modification processor to realize the steps of the method for modifying the wind turbine load estimator according to any one of the above-mentioned aspects.

[0017] In the fourth aspect, the application further provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor realizes the method for modifying the wind turbine load estimator according to any one of the above-mentioned aspects when executing the program.

[0018] In a fifth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for correcting the wind turbine load estimator as described in any one of the above.

[0019] The wind turbine load estimator correction method, device and wind turbine generator set provided by the present invention utilize operating parameters and load measurement parameters under actual working conditions to correct the parameters of the load estimator under target working conditions, thereby improving the accuracy of the load estimator and solving the problem that the practical application of the load estimator is limited. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is one of the flow charts of the correction method of the wind turbine load estimator provided by the present invention;

[0022] Figure 2 The present invention provides Figure 1 Schematic diagram of the process of step 101;

[0023] Figure 3 The present invention provides Figure 1 Flow chart of step 102;

[0024] Figure 4 is a schematic diagram of error decomposition based on the scaling method provided by the present invention;

[0025] Figure 5 This is a principle block diagram of a correction device for a wind turbine load estimator provided by the present invention;

[0026] Figure 6 It is a structural diagram of the high-frequency load estimator provided by the present invention;

[0027] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0028] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0029] It should be noted that, in the description of the embodiments of the present invention, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or also includes elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or apparatus comprising the element.

[0030] The terms "first," "second," and the like in this application are used to distinguish similar objects, and are not used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in orders other than those illustrated or described herein. Furthermore, the objects distinguished by "first," "second," and the like generally refer to a class of objects and do not limit the number of objects. For example, the first object may be one or more.

[0031] The following combination Figures 1 to 4 , briefly describing the wind turbine load estimator correction method, device and wind turbine generator set provided by the embodiments of the present invention.

[0032] Figure 1 This is one of the flow charts of the correction method of the wind turbine load estimator provided by the present invention, such as Figure 1 As shown, including but not limited to the following steps:

[0033] Step 101: obtaining a first wind turbine operating parameter and a first load parameter of a wind turbine generator under a target operating condition, and obtaining a load estimator, wherein the load estimator includes a first conversion matrix set corresponding to a plurality of operating points, wherein the operating points are determined based on a speed and a torque of the wind turbine;

[0034] Specifically, the target operating condition refers to the standard operating condition of the wind turbine, and may also be a set operating condition, where the set operating condition is an operating condition that satisfies the wind speed range of the wind turbine.

[0035] Optionally, the first wind turbine operating parameter and the first load parameter are measured data of the wind turbine under standard operating conditions, which are used to train the load estimator. The trained load estimator can obtain the load estimation parameter based on the acquired wind turbine operating parameters to achieve long-term monitoring of the wind turbine load.

[0036] Optionally, establishing the load estimator includes determining a conversion matrix between the first wind turbine operating parameter and the first load parameter. The expression of the load estimator is as follows:

[0037] Y=ψ(v,τ)*X

[0038] Where Y is the estimated load matrix, X is the sensor measurement parameter matrix, ψ(v, τ) is the first conversion matrix corresponding to a certain operating point, v is the fan speed, and τ is the fan torque. The operating point is determined based on the fan speed and torque. The parameter values ​​of the first conversion matrix corresponding to each operating point are different. The first conversion matrix corresponding to all operating points is combined to obtain the first conversion matrix set.

[0039] Optionally, the models of the wind turbines in this step may be different, and a load estimator is trained for each model of the wind turbine.

[0040] Step 102: obtaining a second wind turbine operating parameter and a second load parameter of the wind turbine under actual working conditions, and obtaining a second conversion matrix set after filtering estimation based on a pre-adjusted filter;

[0041] Specifically, the actual operating condition refers to the current operating condition of the wind turbine after being put into use, and the second wind turbine operating parameter and the second load parameter are the current actual operating data of the wind turbine.

[0042] Optionally, the pre-adjusted filter includes a pre-adjusted optimal linear filter, and the optimal linear filter includes a Wiener filter and a Kalman filter. Below, the present invention is described in detail by taking the Kalman filter as an example.

[0043] Based on a pre-established load estimator, the present invention uses an adjusted Kalman filter to obtain a corrected conversion matrix. The Kalman filter can be used to perform online real-time correction on the load estimator because the Kalman filter algorithm requires little computation and has low requirements on processor performance.

[0044] Optionally, pre-adjusting the Kalman filter includes establishing a Kalman filter equation based on the first conversion matrix set, the second wind turbine operating parameter and the second load parameter, determining a predicted value, an error covariance matrix, a Kalman gain, a filtered estimate and a state covariance matrix estimate.

[0045] Specifically, the wind turbine obtains multiple second conversion matrices under actual operating conditions, and all second conversion matrices are combined to form a second conversion matrix set, wherein the second conversion matrix represents the conversion mapping relationship between the wind turbine operating parameters and load parameters after filtering estimation.

[0046] Step 103: According to the second conversion matrix set, the first conversion matrix set is modified to complete the modification of the wind turbine load estimator.

[0047] Specifically, the first conversion matrix in the first conversion matrix set may be corrected according to the second conversion matrix in the second conversion matrix set.

[0048] Optionally, the load estimator may implement long-term monitoring of the load based on the corrected first conversion matrix set.

[0049] Optionally, the modified first conversion matrix set can also be transplanted to a load estimator of a wind turbine of the same model. The present invention adjusts the structure of the load estimator and uses measured data to modify the load estimator. The modification targets the conversion matrix set in the load estimator, rather than the load estimator output. The modified parameters are then saved, facilitating widespread application of the modified load estimator.

[0050] It can be understood that the present invention uses the operating parameters and load measurement parameters under actual working conditions to correct the parameters of the load estimator under target working conditions, thereby improving the accuracy of the load estimator and solving the problem of limited practical application of the load estimator.

[0051] Figure 2 The present invention provides Figure 1 Flow chart of step 101; Figure 2 Based on the above embodiment, as an optional embodiment, the step of obtaining the first wind turbine operating parameter and the first load parameter of the wind turbine under the target operating condition to obtain the load estimator includes:

[0052] Step 201: obtaining a first wind turbine operating parameter and a first load parameter of the wind turbine under a target operating condition based on simulation software;

[0053] The simulation software used is Bladed. Bladed is a load analysis software platform for wind power design. It can be used for blade and structure modeling, control algorithm simulation, and load analysis of turbine components. Load analysis can help achieve a balance between equipment cost and power generation efficiency.

[0054] Optionally, the first wind turbine operating parameters include but are not limited to nacelle fore-aft acceleration, lateral acceleration, nod acceleration, roll acceleration, motor speed, pitch angle, torque, motor speed average and azimuth angle, and the first load parameters include but are not limited to tower lateral and fore-aft bending moment, hub axial force and torque, blade root bending moment and average wind speed of the wind rotor.

[0055] Step 202 : determining a first conversion matrix set between the first wind turbine operating parameter and the first load parameter based on a regression analysis method to obtain the load estimator.

[0056] Optionally, determining a first conversion matrix set between the first wind turbine operating parameter and the first load parameter based on a regression analysis method includes:

[0057] Decomposing the first fan operating parameter to obtain a high-frequency component of the first fan operating parameter and a low-frequency component of the first fan operating parameter corresponding to a plurality of the operating points;

[0058] Based on the regression analysis method, a conversion matrix between the high-frequency component of the first fan operating parameter and the first load parameter and a conversion matrix between the low-frequency component of the first fan operating parameter and the first load parameter are obtained to obtain the first conversion matrix set.

[0059] Optionally, the high-frequency components of the first wind turbine operating parameters include, but are not limited to, nacelle fore-aft acceleration acc_FA, nacelle lateral acceleration acc_SS, nacelle nod acceleration acc_nod, nacelle roll acceleration acc_roll, and motor speed gen_spd; the low-frequency components of the first wind turbine operating parameters include, but are not limited to, pitch angle pitch, torque (%) torque, motor speed mean gen_spd, and azimuth angle rotor_azim. The estimated loads output by the load estimator include tower Mx, tower My, hub Fx, hub Mx, blade root Mx, blade root My, and rotor average wind speed windspd.

[0060] Optionally, obtaining a conversion matrix between the high-frequency component of the first fan operating parameter and the first load parameter and a conversion matrix between the low-frequency component of the first fan operating parameter and the first load parameter based on a regression analysis method includes: determining a load estimator matrix based on a wavelet analysis method, and determining a value of the matrix based on a least squares method. The load estimator can be expressed by the following formula:

[0061] Y=ψ lf *X lf +ψ hf *X hf =ψ*X

[0062] Among them, ψ lf is the low-frequency component conversion matrix, X lfis a low-frequency component matrix of the first fan operating parameter hf is a high-frequency component conversion matrix, X hf is a high-frequency component matrix of the first fan operating parameter.

[0063] Optionally, in the load estimator application, the working point is determined according to the current rotating speed and torque, and the current conversion matrix is obtained by linear interpolation.

[0064] It can be understood that the first conversion matrix set is obtained by using the regression analysis method, the load estimator is established, and the accuracy of the load estimator is improved by the classification calculation of the high-frequency component and the low-frequency component.

[0065] Figure 3 is provided by the application Figure 1 is a flowchart of step 102 in the application; refer to Figure 3 On the basis of the above embodiment, as an optional embodiment, the second conversion matrix set obtained by the filter based on the pre-adjustment is filtered and estimated, and includes:

[0066] Step 301, according to the second fan operating parameter, the second load parameter and the first conversion matrix set, the Kalman filter state equation and the Kalman filter observation equation at the target time are obtained;

[0067] Step 302, determine the conversion matrix prediction value and error covariance;

[0068] Step 303, according to the error covariance, determine the Kalman gain;

[0069] Step 304, according to the conversion matrix prediction value and the Kalman gain, the second conversion matrix and the error covariance estimation value are obtained.

[0070] Optionally, in step 301, according to the second fan operating parameter, the second load parameter and the first conversion matrix set, the Kalman filter state equation and the Kalman filter observation equation at the target time are obtained, including:

[0071] According to the first conversion matrix set, the Kalman filter state equation at the target time is obtained; the formula of the Kalman filter state equation is as follows:

[0072] ψ[k]=F[k]*ψ[k-1]+w k

[0073] Wherein, ψ[k] is the conversion matrix at the k time, F[k] is the coefficient matrix, if the rotating speed v and the torque τ at k+1 time compared with k time, there is no obvious change, the conversion matrix should also be basically unchanged, F[k] takes the unit matrix.

[0074] According to the second wind turbine operating parameter, the second load parameter and the first conversion matrix set, a Kalman filter observation equation at the target time is obtained. The formula of the Kalman filter observation equation is as follows:

[0075] X -1 [k]=Y -1 [k]ψ[k]+v k

[0076] Among them, X -1 [k] is the inverse of the parameter matrix obtained by the actual measurement of the fan sensor in actual operation, Y -1 [k] is the inverse of the actual measured load matrix.

[0077] In the above two equations, w k and v k is the noise term, and its value satisfies the Gaussian distribution:

[0078] w k ~N(0,R)

[0079] v K ~N(0,Q)

[0080] Where R and Q are selected according to the actual parameter range and experience.

[0081] Optionally, in step 302, the expression for the conversion matrix prediction value is as follows:

[0082]

[0083] in, is the estimated value of the conversion matrix after correction at time k-1.

[0084] The expression of the state error covariance matrix is ​​as follows:

[0085]

[0086] Optionally, in step 303, determining the Kalman gain according to the error covariance includes:

[0087] The Kalman gain is determined based on the error covariance and the second load parameter. The expression of the Kalman gain is as follows:

[0088]

[0089] Where K is the Kalman gain, H[k]=Y -1 [k].

[0090] Optionally, in step 304, obtaining a second conversion matrix and an error covariance estimate based on the conversion matrix prediction value and the Kalman gain includes:

[0091] According to the conversion matrix prediction value, the Kalman gain, the second wind turbine operating parameter and the second load parameter, a second conversion matrix is ​​obtained, and its expression is as follows:

[0092]

[0093] in, is the second conversion matrix.

[0094] The error covariance estimate is obtained according to the Kalman gain, the second load parameter, and the error covariance. The error covariance estimate is expressed as follows:

[0095]

[0096] in, is the estimated value of the state covariance matrix.

[0097] As can be understood, the present invention adjusts the traditional Kalman filter structure and uses actual wind turbine operating data to online correct the conversion matrix set, improving load estimation accuracy and reducing estimation errors caused by discrepancies between training samples and actual operating conditions. Using this adjusted Kalman filter, a high-frequency load estimator with online correction capabilities is more adaptable, facilitating the extension of the estimator from a single wind turbine to other wind turbines of the same type.

[0098] Based on the above embodiment, as an optional embodiment, the step of modifying the first conversion matrix set according to the second conversion matrix set includes:

[0099] According to the second conversion matrix set, the first conversion matrix in the first conversion matrix set is corrected based on a scaling method to complete the correction of the first conversion matrix set.

[0100] Optionally, the modifying the first conversion matrix in the first conversion matrix set based on a scaling method according to the third conversion matrix includes:

[0101] determining a difference in conversion coefficients of target parameters between the third conversion matrix and the first conversion matrix;

[0102] determining a first distance between a conversion coefficient of the target parameter in the first conversion matrix and each normalized working point;

[0103] According to the first distance, the preset second distance and the conversion coefficient difference, the conversion coefficient of each parameter in the first conversion matrix is ​​corrected in turn to complete the correction of the first conversion matrix, wherein the second distance is determined based on the first distance.

[0104] Specifically, Figure 4 Schematic diagram of error decomposition based on scaling method provided by the present invention; Figure 4 As shown in Figure 1, the normalized operating point includes the normalized speed and normalized torque, which can be recorded as interpolation nodes. According to the results of the filtered estimation, the conversion matrix of each interpolation node is corrected. The correction method is:

[0105]

[0106] The first conversion matrix is ​​denoted as χ, χ[i] is the conversion coefficient corresponding to the i-th parameter, and the second conversion matrix after filtering estimation is denoted as ψ′. i is the conversion matrix of the i-th interpolation node, D i It is the distance between the current conversion coefficient and each normalized working point.

[0107] It can be understood that the present invention corrects the parameters in the load estimator through the proportional scaling method, thereby improving the accuracy of the load estimator and avoiding sudden changes in load estimation due to excessive correction.

[0108] The correction device for the wind turbine load estimator provided by the present invention is described below. The correction device for the wind turbine load estimator described below and the correction method for the wind turbine load estimator described above can be referred to each other.

[0109] Figure 5 This is a principle block diagram of the correction device of the wind turbine load estimator provided by the present invention; Figure 5 The present invention further provides a correction device for a wind turbine load estimator, comprising:

[0110] A model determination module 501 is configured to obtain a first wind turbine operating parameter and a first load parameter of the wind turbine under a target operating condition, and obtain a load estimator, wherein the load estimator includes a first conversion matrix set corresponding to a plurality of operating points, wherein the operating points are determined based on a speed and a torque of the wind turbine;

[0111] A matrix determination module 502 is configured to obtain a second wind turbine operating parameter and a second load parameter of the wind turbine under actual operating conditions, and obtain a second conversion matrix set after filtering estimation based on a pre-adjusted filter;

[0112] The parameter correction module 503 is configured to correct the first conversion matrix set according to the second conversion matrix set to complete the correction of the wind turbine load estimator.

[0113] As an optional embodiment, the parameter correction module 503 is configured to:

[0114] According to the second conversion matrix set, the first conversion matrix in the first conversion matrix set is corrected based on a scaling method to complete the correction of the first conversion matrix set.

[0115] As an optional embodiment, the parameter correction module 503 is further configured to:

[0116] determining a difference in conversion coefficients of target parameters between the second conversion matrix and the first conversion matrix;

[0117] determining a first distance between a conversion coefficient of the target parameter in the first conversion matrix and each normalized working point;

[0118] According to the first distance, the preset second distance and the conversion coefficient difference, the conversion coefficient of each parameter in the first conversion matrix is ​​corrected in turn to complete the correction of the first conversion matrix, wherein the second distance is determined based on the first distance.

[0119] As an optional embodiment, the model determination module 501 is configured to:

[0120] Acquire a first wind turbine operating parameter and a first load parameter of the wind turbine under a target operating condition based on simulation software;

[0121] A first conversion matrix set between the first wind turbine operating parameter and the first load parameter is determined based on a regression analysis method to obtain the load estimator.

[0122] As an optional embodiment, the model determination module 501 is configured to:

[0123] Decomposing the first fan operating parameter to obtain a high-frequency component of the first fan operating parameter and a low-frequency component of the first fan operating parameter corresponding to a plurality of the operating points;

[0124] Based on the regression analysis method, a conversion matrix between the high-frequency component of the first fan operating parameter and the first load parameter and a conversion matrix between the low-frequency component of the first fan operating parameter and the first load parameter are obtained to obtain the first conversion matrix set.

[0125] As an optional embodiment, the matrix determination module 502 is configured to:

[0126] Obtaining a Kalman filter state equation and a Kalman filter observation equation at a target time according to the second wind turbine operating parameter, the second load parameter, and the first conversion matrix set;

[0127] Determine the conversion matrix prediction value and error covariance;

[0128] determining a Kalman gain based on the error covariance;

[0129] A second conversion matrix and an error covariance estimate are obtained according to the conversion matrix prediction value and the Kalman gain.

[0130] As an optional embodiment, the matrix determination module 502 is configured to:

[0131] Obtaining a Kalman filter state equation at a target time according to the first conversion matrix set;

[0132] A Kalman filter observation equation at a target time is obtained according to the second wind turbine operating parameter, the second load parameter and the first conversion matrix set.

[0133] As an optional embodiment, the matrix determination module 502 is configured to:

[0134] A Kalman gain is determined according to the error covariance and the second load parameter.

[0135] As an optional embodiment, the matrix determination module 502 is configured to:

[0136] Obtaining a second conversion matrix according to the conversion matrix prediction value, the Kalman gain, the second wind turbine operating parameter, and the second load parameter;

[0137] The error covariance estimate is obtained according to the Kalman gain, the second load parameter, and the error covariance.

[0138] Figure 6 Schematic diagram of the structure of the high-frequency load estimator provided by the present invention; Figure 6 As shown, the present invention also proposes a high-frequency load estimator based on online correction, including a high-frequency load estimator, a filter estimator and an error decomposition module. The high-frequency load estimator is obtained based on a first wind turbine operating parameter and a first load parameter of the wind turbine under a target operating condition, and includes a first conversion matrix set corresponding to multiple operating points, wherein the operating point is determined based on the speed and torque of the wind turbine;

[0139] The filter estimator adjusts the Kalman filter based on the second wind turbine operating parameter and the second load parameter of the wind turbine under actual working conditions, and obtains a second conversion matrix set after filter estimation;

[0140] The error decomposition module is used to correct the first conversion matrix set according to the second conversion matrix set to complete the correction of the wind turbine load estimator.

[0141] It can be understood that the present invention, based on the high-frequency load estimator obtained by the data-driven method, uses a Kalman filter to perform online real-time correction of the estimator parameters according to the actual operation data of the wind turbine, and saves the corrected load estimator, thereby realizing long-term monitoring of the load.

[0142] The present invention also provides a wind turbine generator set, comprising a wind turbine generator set body, in which a wind turbine load estimator correction processor is provided; and further comprising a memory and a program or instruction stored in the memory and executable on the wind turbine load estimator correction processor, wherein when the program or instruction is executed by the wind turbine load estimator correction processor, the steps of the wind turbine load estimator correction method as described in any one of the above items are implemented.

[0143] Figure 7 An example of a physical structure diagram of an electronic device is shown below. Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other via the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the correction method of the wind turbine load estimator, which includes:

[0144] Obtaining a first wind turbine operating parameter and a first load parameter of the wind turbine under a target operating condition to obtain a load estimator, wherein the load estimator includes a first conversion matrix set corresponding to a plurality of operating points, the operating points being determined based on a speed and a torque of the wind turbine;

[0145] Acquire a second wind turbine operating parameter and a second load parameter of the wind turbine under actual working conditions, and obtain a second conversion matrix set after filtering estimation based on a pre-adjusted filter;

[0146] According to the second conversion matrix set, the first conversion matrix set is modified to complete the modification of the wind turbine load estimator.

[0147] Further, the logic instructions in the memory 730 described above can be implemented in the form of software functional units and sold or used as standalone products, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that make contributions to the prior art or parts of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0148] In another aspect, the present application also provides a computer program product, which comprises a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program can be executed by a processor to enable a computer to execute the correction method of the wind turbine load estimator provided by the above-mentioned methods, and the method comprises:

[0149] obtaining first wind turbine operating parameters and first load parameters of the wind turbine under a target working condition to obtain a load estimator, wherein the load estimator comprises a first conversion matrix set corresponding to a plurality of working points, and the working points are determined based on the rotational speed and torque of the wind turbine;

[0150] obtaining second wind turbine operating parameters and second load parameters of the wind turbine under an actual working condition, and obtaining a second conversion matrix set after filtering based on a pre-adjusted filter;

[0151] correcting the first conversion matrix set according to the second conversion matrix set to complete the correction of the wind turbine load estimator.

[0152] In yet another aspect, the present application also provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the correction method of the wind turbine load estimator provided by the above-mentioned methods, and the method comprises:

[0153] obtaining first wind turbine operating parameters and first load parameters of the wind turbine under a target working condition to obtain a load estimator, wherein the load estimator comprises a first conversion matrix set corresponding to a plurality of working points, and the working points are determined based on the rotational speed and torque of the wind turbine;

[0154] Acquire a second wind turbine operating parameter and a second load parameter of the wind turbine under actual working conditions, and obtain a second conversion matrix set after filtering estimation based on a pre-adjusted filter;

[0155] According to the second conversion matrix set, the first conversion matrix set is modified to complete the modification of the wind turbine load estimator.

[0156] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0157] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0158] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A correction method for a wind turbine load estimator, characterized in that: include: Obtaining a first wind turbine operating parameter and a first load parameter of the wind turbine under a target operating condition to obtain a load estimator, wherein the load estimator includes a first conversion matrix set corresponding to a plurality of operating points, the operating points being determined based on a speed and a torque of the wind turbine; Acquire a second wind turbine operating parameter and a second load parameter of the wind turbine under actual working conditions, and obtain a second conversion matrix set after filtering estimation based on a pre-adjusted filter; According to the second conversion matrix set, modifying the first conversion matrix set to complete the modification of the wind turbine load estimator; The modifying the first conversion matrix set according to the second conversion matrix set includes: Determining a difference in conversion coefficients of target parameters between the second conversion matrix and the first conversion matrix; determining a first distance between a conversion coefficient of the target parameter in the first conversion matrix and each normalized working point; Modifying the conversion coefficient of each parameter in the first conversion matrix in sequence according to the first distance, a preset second distance, and the conversion coefficient difference, to complete the modification of the first conversion matrix, wherein the second distance is determined based on the first distance; The modification of the first conversion matrix set is completed.

2. The correction method of the wind turbine load estimator according to claim 1, characterized in that: The step of obtaining a first wind turbine operating parameter and a first load parameter of the wind turbine under a target operating condition to obtain a load estimator includes: Acquire a first wind turbine operating parameter and a first load parameter of the wind turbine under a target operating condition based on simulation software; A first conversion matrix set between the first wind turbine operating parameter and the first load parameter is determined based on a regression analysis method to obtain the load estimator.

3. The correction method of the wind turbine load estimator according to claim 2, characterized in that: The determining of the first conversion matrix set between the first wind turbine operating parameter and the first load parameter based on the regression analysis method includes: Decomposing the first fan operating parameter to obtain a high-frequency component of the first fan operating parameter and a low-frequency component of the first fan operating parameter corresponding to a plurality of the operating points; Based on the regression analysis method, a conversion matrix between the high-frequency component of the first fan operating parameter and the first load parameter and a conversion matrix between the low-frequency component of the first fan operating parameter and the first load parameter are obtained to obtain the first conversion matrix set.

4. The correction method of the wind turbine load estimator according to claim 1, characterized in that: The second conversion matrix set obtained after filtering estimation based on the pre-adjusted filter includes: Obtaining a Kalman filter state equation and a Kalman filter observation equation at a target time according to the second wind turbine operating parameter, the second load parameter, and the first conversion matrix set; Determine the conversion matrix prediction value and error covariance; determining a Kalman gain based on the error covariance; A second conversion matrix and an error covariance estimate are obtained according to the conversion matrix prediction value and the Kalman gain.

5. The correction method of the wind turbine load estimator according to claim 4, characterized in that: The step of obtaining the Kalman filter state equation and the Kalman filter observation equation at the target time according to the second wind turbine operating parameter, the second load parameter, and the first conversion matrix set includes: Obtaining a Kalman filter state equation at a target time according to the first conversion matrix set; A Kalman filter observation equation at a target time is obtained according to the second wind turbine operating parameter, the second load parameter and the first conversion matrix set.

6. The correction method of the wind turbine load estimator according to claim 4, characterized in that: Determining the Kalman gain according to the error covariance includes: A Kalman gain is determined according to the error covariance and the second load parameter.

7. The correction method of the wind turbine load estimator according to claim 4, characterized in that: The obtaining, according to the conversion matrix prediction value and the Kalman gain, a second conversion matrix and an error covariance estimate, comprises: Obtaining a second conversion matrix according to the conversion matrix prediction value, the Kalman gain, the second wind turbine operating parameter, and the second load parameter; The error covariance estimate is obtained according to the Kalman gain, the second load parameter, and the error covariance.

8. A correction device for a wind turbine load estimator, characterized in that: A method for correcting a wind turbine load estimator according to any one of claims 1 to 7, the device comprising: a model determination module, configured to obtain a first wind turbine operating parameter and a first load parameter of the wind turbine under a target operating condition, and obtain a load estimator, wherein the load estimator includes a first conversion matrix set corresponding to a plurality of operating points, wherein the operating points are determined based on a speed and a torque of the wind turbine; a matrix determination module, configured to obtain a second wind turbine operating parameter and a second load parameter of the wind turbine under actual operating conditions, and obtain a second conversion matrix set after filtering estimation based on a pre-adjusted filter; A parameter correction module is used to correct the first conversion matrix set according to the second conversion matrix set to complete the correction of the wind turbine load estimator.

9. A wind turbine generator system, characterized in that: The invention comprises a wind turbine generator set body, in which a wind turbine load estimator correction processor is provided; and further comprises a memory and a program or instruction stored in the memory and executable on the wind turbine load estimator correction processor, wherein when the program or instruction is executed by the wind turbine load estimator correction processor, the steps of the wind turbine load estimator correction method according to any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for correcting the wind turbine load estimator according to any one of claims 1 to 7 is implemented.

11. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for correcting the wind turbine load estimator according to any one of claims 1 to 7 is implemented.

Images