Wind turbine generator yaw adaptive calibration method and system based on big data

Abstract

The invention discloses a wind turbine generator yaw adaptive calibration method and system based on big data, and relates to the field of wind turbine generator yaw adaptive calibration. The method comprises the steps that a brake geometric model is generated based on a yaw brake, an operation load spectrum is introduced into the brake geometric model, and the yaw moment change rule of the yaw brake is analyzed; the strength limit value of the yaw brake is analyzed according to the yaw moment change rule and the simulation technology, and the operation cycle of deflection of the wind turbine generator caused by braking failure of the yaw brake is analyzed based on the strength limit value; the change relation between the wind turbine generator and the deflection speed is predicted through the operation cycle, and a friction coefficient self-adaptive adjustment strategy of the yaw brake is generated according to the change relation; and according to the wind direction information, a calibration scheme is matched from the friction coefficient self-adaptive adjustment strategy, and wind turbine generator yaw self-adaptive calibration operation is executed. According to the method, accurate control over the yaw moment is achieved, the moment is prevented from being too large or too small, and the performance of a yaw system is optimized.

Description

Technical Field

[0001] The present invention relates to the field of wind turbine yaw adaptive calibration, and in particular to a wind turbine yaw adaptive calibration method and system based on big data. Background Art

[0002] Wind turbines are devices that convert wind energy into electrical energy and are the core components of modern wind power generation systems. Wind turbines capture wind energy through wind rotors and convert it into usable electricity through mechanical and electrical systems. As the core equipment for wind power generation, wind turbines play an important role in daily life, and their technological progress will further promote the sustainable development of the wind power industry.

[0003] The yaw system of a wind turbine is an important component of a wind turbine generator set. Its main function is to adjust the direction of the wind rotor so that it is always facing the incoming wind direction, thereby maximizing the efficiency of capturing wind energy. The yaw system of a wind turbine mainly includes a yaw motor, a yaw brake, a yaw gear ring and a control system. The yaw system of a wind turbine can make the wind rotor always face the incoming wind direction, capture maximum wind energy, and improve the power generation efficiency of the wind turbine. At the same time, in complex terrain or changeable wind conditions, the yaw system ensures that the wind turbine can quickly respond to changes in wind direction. Therefore, the yaw system of a wind turbine is one of the core technologies to ensure the efficient operation of a wind turbine. Its accuracy and reliability directly affect the power generation efficiency and service life of the unit.

[0004] In the existing yaw control process of wind turbines, it is impossible to accurately quantify the wear value of the yaw brake under different working conditions, establish a quantitative relationship between the wear coefficient and the working condition and yaw moment intensity, and quantify the impact of the working condition and yaw moment on the brake performance. As a result, it is impossible to predict the operating cycle of the deflection after the yaw brake fails, and it is impossible to estimate in advance the deflection cycle of the wind turbine after the brake fails, laying the foundation for providing a time window for operation and maintenance.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes a wind turbine yaw adaptive calibration method and system based on big data, which achieves the purpose of fully optimizing the performance of the yaw system and improving the safety of the wind turbine.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention provides a wind turbine yaw adaptive calibration method based on big data, the wind turbine yaw adaptive calibration method comprising:

[0009] The brake geometry model is generated based on the combination of the yaw brake and 3D modeling software, and the operating load spectrum is introduced into the brake geometry model to analyze the variation law of the yaw moment of the yaw brake;

[0010] The strength limit of the yaw brake is analyzed according to the yaw moment variation law and simulation technology, and based on the strength limit, the operation cycle of the wind turbine deflection caused by the yaw brake failure is analyzed;

[0011] Predict the changing relationship between the wind turbine and the yaw speed and wind direction information through the operation cycle, and generate an adaptive adjustment strategy for the friction coefficient of the yaw brake based on the changing relationship;

[0012] Based on big data, the wind direction information at the wind turbine in the future period is obtained, and the calibration scheme is matched from the friction coefficient adaptive adjustment strategy according to the wind direction information. The calibration scheme is transmitted to the yaw brake controller to perform the wind turbine yaw adaptive calibration operation.

[0013] Preferably, a brake geometric model is generated based on the yaw brake in combination with a three-dimensional modeling software, and the operating load spectrum is introduced into the brake geometric model, and the yaw moment variation law of the yaw brake is analyzed, including:

[0014] Obtaining geometric structural parameters of the yaw brake, combining the 3D modeling software with the geometric structural parameters to construct a geometric model of the yaw brake, and introducing the geometric model of the yaw brake into the finite element analysis software to perform assembly adjustment of the geometric model of the yaw brake;

[0015] Extracting load data of the yaw brake during actual operation based on a data acquisition monitor, and formulating a load spectrum of the yaw brake according to the load data to obtain an operating load spectrum;

[0016] Define the material properties and contact relationships of the yaw brake geometry model in the finite element analysis software, mesh the yaw brake geometry model, and apply boundary conditions and load information;

[0017] The operating load spectrum is introduced into the brake geometric model, and the yaw moment of the yaw brake after the load spectrum is applied is calculated using finite element analysis software. After the calculation is completed, the change law of the yaw moment is analyzed.

[0018] Preferably, the strength limit of the yaw brake is analyzed according to the yaw moment variation law and simulation technology, and the operation cycle of the wind turbine generator set deflection caused by the yaw brake failure is analyzed based on the strength limit, including:

[0019] Based on the variation law of yaw moment, the wear value of yaw brake in yaw process under different working conditions is analyzed by dimensional analysis and numerical simulation technology, and the influence of yaw moment intensity on wear value is analyzed;

[0020] Establish the wear coefficient based on the impact analysis, determine the quantitative relationship between the wear coefficient and the operating conditions and the yaw moment strength, and use the quantitative relationship to obtain the use strength limit of the yaw brake when operating under preset conditions;

[0021] The variable set method is used to calculate the relative fuzziness of the use intensity limit value, obtain the level characteristic value, and use the partial connection coefficient technology to explore the impact of the deflection of the wind turbine on the level characteristic value, and obtain the periodic classification strategy based on the impact results;

[0022] The operation period of wind turbine deflection after yaw brake failure is estimated based on the use of intensity limit and cycle rating strategy.

[0023] Preferably, based on the variation law of the yaw moment, the wear value of the yaw brake during the yaw process under different working conditions is analyzed by using dimensional analysis and numerical simulation technology, and the influence of the yaw moment intensity on the wear value is analyzed, including:

[0024] Based on the variation law of yaw moment and dimensional analysis, the dimensional relationship between the wind wheel, yaw bearing and yaw motor is established, and the dimensionless quantity is set to convert the dimensional relationship into a dimensionless function;

[0025] The dimensionless function is used to generate the numerical simulation set of the wind rotor, yaw bearing and yaw motor, and the numerical simulation set is combined with the brake geometric model to analyze the yaw drive process under different numerical simulation sets.

[0026] The working temperature distribution of the yaw drive is analyzed according to the yaw drive process, and the exponential relationship between the yaw moment and the temperature is established based on the working temperature distribution. The exponential relationship is used to determine the wear value of the yaw drive under different working conditions.

[0027] The wear value is matched with the corresponding yaw moment, the changing relationship between the yaw moment intensity and the wear value is analyzed, and the influence of the yaw moment intensity on the wear value is determined based on the changing relationship.

[0028] Preferably, establishing a wear coefficient according to the impact analysis, determining the quantitative relationship between the wear coefficient and the working condition and the yaw moment strength, and using the quantitative relationship to obtain the use strength limit of the yaw brake when operating under preset conditions includes:

[0029] The wear coupling coefficient of the yaw brake is defined based on the influence relationship and the working temperature distribution, and the quality coefficient is set using dimensional technology to analyze the correlation between the wear coupling coefficient and different working conditions.

[0030] Determine the trend difference between the correlation relationship and the exponential relationship, and determine the coupling constant under different working conditions based on the trend difference results, and determine the quantitative relationship between the wear coefficient and the wear work under different working conditions based on the coupling constant;

[0031] The quantitative relationship between wear and tear and the coupling constant is combined to determine the quantitative relationship between wear coefficient and yaw moment strength, and the operating conditions of the yaw brake are preset according to the quantitative relationship between wear and tear and the quantitative relationship between yaw moment strength.

[0032] The operating conditions are used to obtain the usage intensity of the yaw brake during operation, and the corresponding upper and lower strength limits are screened from the usage intensity results to obtain the usage intensity limit.

[0033] Preferably, the relative fuzziness of the use intensity limit is calculated by using a variable set method to obtain the level characteristic value, and the partial connection coefficient technology is used to explore the impact of the deflection of the wind turbine on the level characteristic value. The cycle rating strategy based on the impact result includes:

[0034] Based on setting the intensity set using the intensity limit, the interval matrix of the upper and lower limits of the intensity is divided according to the intensity set, and the variable set opposition technology is used to search for the gradual change point using the intensity limit in the intensity set;

[0035] Generate a variable set matrix using the gradually changing metamorphic point and interval matrix, determine the positional relationship of the use intensity limit value in the variable set matrix, and calculate the relative ambiguity of the use intensity limit value based on the positional relationship;

[0036] According to the relative fuzziness analysis, the strength limit value is used to calculate the total relative fuzziness of the wear coefficient, and the level characteristic values ​​corresponding to different working conditions are calculated based on the total relative fuzziness;

[0037] The nonlinear relationship between the deflection angle and the level characteristic value is calculated using the partial connection coefficient technology, and the influence of the deflection angle on the level characteristic value is analyzed based on the nonlinear relationship results;

[0038] Based on the influence relationship, the sensitive interval and threshold between the deflection angle and the level characteristic value are determined, and a periodic grading strategy is generated according to the sensitive interval and threshold.

[0039] Preferably, the calculation formula of relative ambiguity is:

[0040]

[0041] The calculation formula of the level characteristic value is:

[0042]

[0043] In the formula, β represents the relative ambiguity, b ih represents the service strength limit under the i-th working condition, c ij represents the position relationship under the i-th working condition, h ih represents the hth gradual deterioration point under the i-th working condition, δ represents the level characteristic value, h represents the service strength limit, uj (v h ) represents the total relative fuzziness under the jth wear coefficient condition, h i(h+1) It represents the h+1th gradual degradation point under the i-th operating condition.

[0044] Preferably, predicting the changing relationship between the wind turbine and the yaw speed and wind direction information through the operation cycle, and generating a friction coefficient adaptive adjustment strategy for the yaw brake according to the changing relationship includes:

[0045] The wind direction information, deflection angle and working status data of the yaw brake during the historical operation of the wind turbine are obtained by using a data acquisition monitor and combined as the benchmark data;

[0046] Based on the Monte Carlo method, the benchmark data is extracted to analyze the probability density function of the deflection angle and working status under different wind direction information, and the scale change probability is divided according to the probability density function and Newton's method;

[0047] According to the scale change probability and fuzzy mathematical theorem, the wind direction information is classified to build a change period prediction model, and the change relationship between the wind turbine and the deflection speed and wind direction information is clarified;

[0048] According to the changing relationship of the prediction model output during the changing period, the heat treatment control instructions are generated in combination with the deflection speed under different wind speeds and wind directions and the working state of the yaw brake, and the adaptive adjustment strategy of the yaw brake friction coefficient is determined.

[0049] Preferably, the benchmark data is extracted based on the Monte Carlo method to analyze the probability density function of the deflection angle and the working state under different wind direction information, and the scale change probability is divided according to the probability density function and the Newton method, including:

[0050] The deflection angle and working state are set as scale feature and spatial feature respectively, and the Monte Carlo method is used to randomly extract data from the benchmark data to clarify the spatiotemporal distribution of wind direction information.

[0051] The similarity between the spatiotemporal distribution of wind direction information and the normal distribution is analyzed, and the probability density function is defined based on the similarity results. The root of the probability density function is approximated by using the Newton method.

[0052] Based on the root results, the change load of the deflection angle and the working state is clarified, and the scale change probability is divided according to the change load results.

[0053] In a second aspect, the present invention further provides a wind turbine yaw adaptive calibration system based on big data, the wind turbine yaw adaptive calibration system comprising:

[0054] The yaw moment change analysis module is used to generate a brake geometry model based on the yaw brake combined with 3D modeling software, and introduce the operating load spectrum into the brake geometry model to analyze the yaw moment change law of the yaw brake;

[0055] An operation cycle acquisition and analysis module is used to analyze the strength limit of the yaw brake according to the yaw moment change law and simulation technology, and to analyze the operation cycle of the wind turbine deflection caused by the yaw brake failure based on the strength limit;

[0056] A yaw adjustment strategy generation module is used to predict the changing relationship between the wind turbine and the yaw speed and wind direction information through the operation cycle, and generate a friction coefficient adaptive adjustment strategy for the yaw brake according to the changing relationship;

[0057] The adaptive calibration operation module is used to obtain the wind direction information at the wind turbine in the future period based on big data, match the calibration plan from the friction coefficient adaptive adjustment strategy according to the wind direction information, transmit the calibration plan to the yaw brake controller, and perform the wind turbine yaw adaptive calibration operation.

[0058] The beneficial effects of the present invention are:

[0059] 1. The present invention analyzes the variation law of yaw moment based on the yaw brake geometric model and operating load spectrum, which is helpful to predict the stress state of wind turbines under different operating conditions, clarify potential problems in design and operation, and analyze the strength limit of the yaw brake and the deflection period caused by brake failure to ensure that the yaw brake operates within a safe load range and reduce the risk of equipment damage due to overload. Through the prediction of the deflection period, a more reasonable yaw strategy is formulated to reduce the excessive use of the yaw system and extend the life of the brake. In addition, the adaptive adjustment strategy of the friction coefficient of the yaw brake can dynamically adapt to different wind conditions, realize precise control of the yaw moment, avoid excessive or insufficient torque, comprehensively optimize the performance of the yaw system, and improve the safety, stability and economic benefits of the wind turbine.

[0060] 2. The present invention accurately quantifies the wear value of the yaw brake under different working conditions through the yaw moment change law and numerical simulation, and establishes a quantitative relationship between the wear coefficient and the working condition and the yaw moment intensity, quantifies the influence of the working condition and yaw moment on the brake performance, and clarifies the safe operating conditions of the equipment. At the same time, the variable set method is used to calculate the relative ambiguity, obtain the level eigenvalues ​​and explore the influence of the deflection on the eigenvalues, which is convenient for dividing the operating status of the yaw brake and helps the operation and maintenance personnel to grasp the equipment status in real time. Finally, based on the strength limit and the periodic grading strategy, the operating cycle of the deflection of the yaw brake after the braking failure is predicted, which can realize the early estimation of the deflection period of the wind turbine after the brake failure, and provide a time window for operation and maintenance.

[0061] 3. The present invention constructs a basic database for wind turbine operation by acquiring historical wind direction information, deflection angle and yaw brake working status data, laying a solid foundation for subsequent analysis, and using the Monte Carlo method to simulate the uncertainty in complex systems through random sampling, providing a more reliable probability distribution model for the yaw system. At the same time, the wind direction information is classified through fuzzy mathematics to construct a prediction model, revealing the relationship between the deflection speed of the wind turbine and the change in wind direction. Combined with real-time data of wind speed, wind direction and deflection speed, the friction coefficient is controlled through heat treatment, the working state of the yaw brake is optimized, and the mechanical damage caused by excessive or insufficient friction is reduced. Reasonable adjustment of the friction coefficient reduces excessive wear, thereby extending the service life of the yaw brake. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0063] Figure 1 is a flow chart of a method for adaptive yaw calibration of a wind turbine based on big data according to an embodiment of the present invention;

[0064] Figure 2 It is a principle block diagram of a wind turbine yaw adaptive calibration system based on big data according to an embodiment of the present invention.

[0065] In the figure:

[0066] 1. Yaw moment change analysis module; 2. Operation cycle acquisition analysis module; 3. Yaw adjustment strategy generation module; 4. Adaptive calibration operation module. DETAILED DESCRIPTION

[0067] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0068] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0069] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0070] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0071] See also Figure 1 The present invention provides a wind turbine yaw adaptive calibration method based on big data, and the wind turbine yaw adaptive calibration method includes:

[0072] Step S1: Generate a brake geometric model based on the yaw brake in combination with three-dimensional modeling software, introduce the operating load spectrum into the brake geometric model, and analyze the yaw moment variation rule of the yaw brake.

[0073] In this embodiment, when a brake geometric model is generated based on the yaw brake in combination with three-dimensional modeling software, and the operating load spectrum is introduced into the brake geometric model to analyze the variation law of the yaw moment of the yaw brake, the geometric structure parameters of the yaw brake can be obtained, the three-dimensional modeling software and the geometric structure parameters are combined to construct the yaw brake geometric model, and the yaw brake geometric model is introduced into the finite element analysis software to perform assembly adjustment of the yaw brake geometric model; based on the data acquisition monitor, the load data of the yaw brake during actual operation is extracted, and the load spectrum of the yaw brake is formulated according to the load data to obtain the operating load spectrum; the material properties and contact relationship of the yaw brake geometric model are defined in the finite element analysis software, the yaw brake geometric model is meshed, and boundary conditions and load information are applied; the operating load spectrum is introduced into the brake geometric model, and the yaw moment of the yaw brake after the load spectrum is applied is calculated using the finite element analysis software, and the variation law of the yaw moment is analyzed after the calculation is completed.

[0074] It should be explained that the steps for analyzing the variation of yaw moment based on the combination of yaw brake and 3D modeling software and the introduction of operating load spectrum are as follows:

[0075] Step 1: Generate a yaw brake geometric model;

[0076] Use 3D modeling software (such as SolidWorks, CATIA or AutoCAD) to establish the geometric model of the yaw brake. The input parameters include geometric structure parameters (such as brake radius, thickness, friction pad size, gear ring diameter, etc.). The brake R radius is 1.5m, the friction pad G thickness is 0.05m, and the gear ring diameter D is 4.0m. Export the modeled brake to a standard geometric format file (such as STL or STEP) to facilitate the subsequent introduction of finite element analysis software.

[0077] Step 2: Introduce the geometric model into the finite element analysis software and make assembly adjustments;

[0078] Import the geometric model into finite element analysis software (such as ANSYS, ABAQUS), and adjust the model: define the relative position of the brake and the gear ring, and the contact area between the brake pad and the brake disc; the assembly parameters include the contact area of ​​the friction surface is 0.3m 2 , the contact gap is 0.001m;

[0079] Use the data acquisition monitor to extract the actual operating load data of the yaw brake (such as wind load, friction force, braking torque). Example data range: wind load F wind =100~400kN, yaw friction force F friction =20~80kN;

[0080] Generate load spectrum based on load data: pulse load (simulates the impact force caused by strong wind in a short period of time); periodic load (simulates the impact of wind speed changes on brakes during long-term operation);

[0081] Example load spectrum: F(t) = 200 + 50·sin(2πt), which represents the sinusoidal variation of wind load over time.

[0082] Step 3: Define material properties and contact relationships;

[0083] The brake material in the material property definition is alloy steel; elastic modulus E = 2.1 × 10 11 Pa; Poisson's ratio T = 0.3; yield strength σ y =250MPa;

[0084] The elastic modulus of the composite material in the friction pad material is E = 3.0 × 10 9 Pa; friction coefficient μ = 0.4;

[0085] Contact relationship definition: Set the contact type between the brake pad and the gear ring to friction contact, friction coefficient: 0.3~0.6 (adjusted with load).

[0086] Step 4: Mesh division and boundary condition setting;

[0087] Select the appropriate unit type (tetrahedron or hexahedron) according to the geometric complexity of the brake;

[0088] Example: The number of grid cells N = 100000, the grid size Δx = 0.01m, the fixed constraint in the boundary condition setting is that the bottom of the gear ring is completely fixed, and the load application is to apply wind load and friction along the direction of rotation of the wind rotor;

[0089] The operating load spectrum is introduced into the geometric model to calculate the yaw moment of the yaw brake at different time points: M yaw =F friction ·R;

[0090] Example results: When the wind load is 200kN, the yaw moment M yaw =60kNm; when the wind load is 00kN, the yaw moment M yaw =120kNm; record the curve of yaw moment changing with time and analyze its law.

[0091] Step 5: Analyze the changing law of yaw moment;

[0092] Plot the yaw moment versus time or load. Example: M yaw =50+10·cos(2πt). The analysis rule is that the yaw moment is proportional to the wind load, and the increase of friction coefficient will significantly increase the yaw moment.

[0093] Step S2: analyzing the strength limit of the yaw brake according to the yaw moment variation law and simulation technology, and analyzing the operation cycle of the wind turbine generator set deflection caused by the yaw brake failure based on the strength limit.

[0094] In this embodiment, when analyzing the strength limit of the yaw brake according to the yaw moment variation law and simulation technology, and analyzing the operating period of the wind turbine deflected due to the yaw brake failure based on the strength limit, the wear value of the yaw brake in the yaw process under different working conditions can be analyzed by using dimensional analysis and numerical simulation technology based on the yaw moment variation law, and the influence of the yaw moment strength on the wear value can be analyzed; a wear coefficient is established according to the influence analysis, and the quantitative relationship between the wear coefficient and the working condition and the yaw moment strength is determined, and the use strength limit of the yaw brake when operating under preset conditions is obtained by using the quantitative relationship; the relative fuzziness of the use strength limit is calculated by using the variable set method to obtain the level characteristic value, and the deviating coefficient technology is used to explore the influence of the deflection of the wind turbine on the level characteristic value, and the period classification strategy is obtained based on the influence result; the operating period of the wind turbine deflection after the yaw brake failure is estimated based on the use strength limit and the period classification strategy.

[0095] In this embodiment, based on the yaw moment variation law, dimensional analysis and numerical simulation technology are used to analyze the wear value of the yaw brake in the yaw process under different working conditions, and the influence of the yaw moment intensity on the wear value is analyzed. A dimensional relationship between the wind wheel, the yaw bearing and the yaw motor can be established based on the yaw moment variation law and dimensional analysis, and a dimensionless quantity is set to convert the dimensional relationship into a dimensionless function; a dimensionless function is used to generate a numerical simulation set of the wind wheel, the yaw bearing and the yaw motor, and the numerical simulation set is combined with the brake geometric model to analyze the yaw drive process under different numerical simulation sets; the working temperature distribution of the yaw drive is analyzed according to the yaw drive process, and an exponential relationship between the yaw moment and the temperature is established based on the working temperature distribution, and the exponential relationship is used to judge the wear value of the yaw drive under different working conditions; the wear value is matched with the corresponding yaw moment, the changing relationship between the yaw moment intensity and the wear value is analyzed, and the influence of the yaw moment intensity on the wear value is judged according to the changing relationship.

[0096] In this embodiment, when establishing the wear coefficient according to the influence analysis, judging the quantitative relationship between the wear coefficient and the working condition and the yaw moment strength, and using the quantitative relationship to obtain the usage intensity limit of the yaw brake when operating under preset conditions, the wear coupling coefficient of the yaw brake can be defined based on the influence relationship and the working temperature distribution, and the quality coefficient can be set using the dimensional technology to analyze the correlation between the wear coupling coefficient and different working conditions to judge the trend difference between the correlation relationship and the exponential relationship, and judge the coupling constant under different working conditions based on the trend difference results, and determine the wear quantitative relationship between the wear coefficient and different working conditions based on the coupling constant; combine the wear quantitative relationship with the coupling constant to judge the eccentric loss quantitative relationship between the wear coefficient and the yaw moment strength, and preset the operating conditions of the yaw brake based on the wear quantitative relationship and the eccentric loss quantitative relationship; use the operating conditions to obtain the usage intensity of the yaw brake during operation, and filter the corresponding upper and lower strength limits from the usage intensity results to obtain the usage intensity limit.

[0097] In this embodiment, when the relative fuzziness of the use intensity limit is calculated by using the variable set method, the level characteristic value is obtained, and the partial connection coefficient technology is used to explore the influence of the deflection of the wind turbine on the level characteristic value, and the periodic grading strategy is obtained based on the influence result, the intensity set can be set based on the use intensity limit, and the interval matrix of the upper and lower limits of the intensity can be divided according to the intensity set. The variable set opposition technology is used to search for the gradual change point of the use intensity limit in the intensity set; the variable set matrix is ​​generated by using the gradual change point and the interval matrix, and the position relationship of the use intensity limit in the variable set matrix is ​​determined, and the relative fuzziness of the use intensity limit is calculated based on the position relationship; the total relative fuzziness of the use intensity limit to the wear coefficient is analyzed according to the relative fuzziness, and the level characteristic values ​​corresponding to different working conditions are calculated based on the total relative fuzziness; the nonlinear relationship between the deflection angle and the level characteristic value is calculated by using the partial connection coefficient technology, and the influence relationship of the deflection angle on the level characteristic value is analyzed according to the nonlinear relationship result; the sensitive interval and threshold between the deflection angle and the level characteristic value are determined based on the influence relationship, and the periodic grading strategy is generated according to the sensitive interval and threshold.

[0098] Specifically, the calculation formula of relative ambiguity is:

[0099]

[0100] The calculation formula of the level characteristic value is:

[0101]

[0102] In the formula, β represents the relative ambiguity, b ih represents the service strength limit under the i-th working condition, c ij represents the position relationship under the i-th working condition, h ih represents the hth gradual deterioration point under the i-th working condition, δ represents the level characteristic value, h represents the service strength limit, u j (v h ) represents the total relative fuzziness under the jth wear coefficient condition, h i(h+1) It represents the h+1th gradual degradation point under the i-th operating condition.

[0103] In order to facilitate understanding of the above technical solution of this embodiment, the operation method of this embodiment in the actual process is described in detail below.

[0104] Step 1: Analysis of yaw brake wear value;

[0105] Establish the dimensional relationship between the wind wheel, yaw bearing and yaw motor: M yaw =f(R,F friction ,E,ν,T);M yawrepresents the yaw moment, in N·m; R represents the radius of the yaw brake, 1.5m; F friction represents friction force, 20 to 80 kN; E represents the elastic modulus of the material, 2.1×10 11 Pa; ν represents the Poisson's ratio of the material, 0.3; T represents the temperature, 300~500K;

[0106] Through dimensionless analysis:

[0107]

[0108] Π3=v;

[0109]

[0110] Where, T ref =300K, set simulation parameters: F friction =40kN and 60kN, T = 350K and 400K, R = 1.5m;

[0111] Formula to define wear value: W = kF friction RT; wear coefficient = 2 × 10 -6 ;

[0112] When F friction =40kN, R=1.5m, T=400K, W=2×10 -6 ·40·10 3 1.5 400 = 48 mm 3 ;

[0113] When F friction =60kN, R=350, T=350K, W=2×10 -6 ·60·10 3 1.5 350 = 63 mm 3 .

[0114] Step 2: Wear coefficient and strength limit analysis;

[0115] Define the wear coupling coefficient:

[0116]

[0117] When M yaw =81.87N·m, W=48mm 3 , when T=400K, C w =1.47×10 -3 ; When M yaw =90N·m, W=63mm 3 , when T=350K, C w =2.0×10-3 ;

[0118] Then fit the wear coefficient formula: k w =a+b·C w , coefficient a = 0.0, b = 5.0;

[0119] When C w =1.47×10 -3 When k w =0.01735, when C w =2.0×10 -3 When k w =0.02.

[0120] Step 3: Use intensity limits and cycle rating strategies;

[0121] Define strength limit: S limit =S upper -S lower Upper limit S upper =100MPa, lower limit S lower =80MPa, S limit =100-80=20MPa;

[0122] Calculate the relative ambiguity and generate a strategy based on the ambiguity and deflection angle sensitive range (10°~15°): ambiguity β≤0.5: operation cycle is 10000min; ambiguity β>0.5: operation cycle is 8000min.

[0123] Step 4: the yaw cycle of the wind turbine after the yaw brake fails;

[0124] Estimate the operating period after yaw brake failure using strength limits:

[0125]

[0126] When S limit =20MPa, k w =0.01735, W = 48mm 3 , T operation =23993min; when k w =0.02, W = 63mm 3 , T operation =15873min.

[0127] Furthermore, through dimensional analysis, numerical simulation and fuzzy technology, the wear value, wear coefficient and its influence on the yaw moment of the yaw brake under different working conditions were calculated. The operating cycle of the wind turbine yaw brake after failure was estimated by combining the strength limit and cycle classification strategy, which provides an important reference for the optimization and operating cycle management of the yaw system.

[0128] Step S3: predicting the changing relationship between the wind turbine and the yaw speed and wind direction information through the operation cycle, and generating a friction coefficient adaptive adjustment strategy for the yaw brake according to the changing relationship.

[0129] In this embodiment, when predicting the changing relationship between the wind turbine and the deflection speed and wind direction information through the operation cycle, and generating an adaptive adjustment strategy for the friction coefficient of the yaw brake based on the changing relationship, the data acquisition monitor can be used to obtain the wind direction information, deflection angle and working status data of the yaw brake during the historical operation of the wind turbine as benchmark data; the benchmark data is extracted based on the Monte Carlo method to analyze the probability density function of the deflection angle and the working status under different wind direction information, and the scale change probability is divided according to the probability density function and Newton's method; the wind direction information is classified according to the scale change probability and fuzzy mathematical theorem to construct a change period prediction model, and the changing relationship between the wind turbine and the deflection speed and wind direction information is clarified; according to the changing relationship output by the change period prediction model, the heat treatment control instructions are generated in combination with the deflection speed under different wind speeds and wind directions and the working status of the yaw brake to determine the adaptive adjustment strategy for the friction coefficient of the yaw brake.

[0130] In this embodiment, when extracting benchmark data based on the Monte Carlo method to analyze the probability density function of the deflection angle and the working state under different wind direction information, and dividing the scale change probability according to the probability density function and the Newton method, the deflection angle and the working state can be set as the scale characteristic quantity and the spatial characteristic quantity respectively, and the Monte Carlo method is used to randomly extract data from the benchmark data to clarify the spatiotemporal distribution of the wind direction information; analyze the similarity between the spatiotemporal distribution of the wind direction information and the normal distribution, define the probability density function based on the similarity results, and use the Newton method to iteratively approximate the root of the probability density function; clarify the change load of the deflection angle and the working state based on the root result, and divide the scale change probability according to the change load result.

[0131] In this embodiment, when classifying wind direction information according to scale change probability and fuzzy mathematical theorem to construct a change period prediction model and clarify the change relationship between wind turbines and deflection speed and wind direction information, the scale change probability can be fitted based on the probability density function, and the distribution of each interval can be fitted according to different wind direction intervals. A fuzzy membership function is defined based on wind direction information and deflection speed, and the wind direction data is classified using the fuzzy membership function. At the same time, the time series change rate of the deflection speed is calculated to analyze the change periods of different wind direction intervals, such as stable periods and rapid change periods. A change period prediction model is constructed based on fuzzy rules, and the wind direction classification results are used to fit the change relationship of the deflection speed to summarize the change law.

[0132] In order to facilitate understanding of the above technical solution of the present embodiment, the method for generating the adaptive friction coefficient adjustment strategy in the actual process of the present embodiment is described in detail below.

[0133] Step 1: Data collection and benchmark data construction;

[0134] The following data are obtained through the wind turbine data acquisition monitor:

[0135] The wind direction information (θ) is 0° to 360°, with a sampling interval of 10°, for a total of 36 intervals; the deflection angle (α) is -30° to +30°, sampled in units of 5°, for a total of 13 intervals.

[0136] Yaw brake working status (S brake ), set the normal working state in three states (S normal ) is the deflection velocity v yaw ≤2° / s; overload (S overload ) is 2° / s <v yaw ≤5° / s; Failure (S failure ) is v yaw >5° / s;

[0137] One year of data (N = 10,000 data points) was collected to generate a benchmark data set using random sampling. The combined frequency distribution of wind direction and deflection angle, working status and wind speed (v wind ) relationship table.

[0138] Step 2: Monte Carlo analysis and scale change probability division;

[0139] Normal distribution fitting of deflection angle λ: μ λ =0°,σ λ =10°;

[0140] The probability density function is:

[0141]

[0142] Working status brake Normal distribution fitting: Normal working is μ S =1° / s,σ S =0.5° / s; overload is μ S =3.5° / s,σ S =0.5° / s;

[0143] The Newton method is used to solve the root of the probability density function, and the load range of the deflection angle λ in the boundary point (root) is determined as normal operation λ∈[-10°, 10°]; overload λ∈[10°, 20°].

[0144] Newton's method iterative solution:

[0145]

[0146] The critical point is calculated: λ critical1 =9.8°(normal and overload critical);λ critical2 =19.6°(overload and failure critical);

[0147] According to the probability density results, the scale change probability is divided: the probability of normal working state is P normal =0.68; the probability of overload state is P overload =0.27; the probability of failure is P failure =0.05.

[0148] Step 3: Fuzzy mathematics classification and change period prediction model;

[0149] Fuzzy membership function definition of wind direction information fuzzy set: low wind speed (F low ) is v wind ≤5m / s; medium wind speed (F medium ) is 5m / s <v wind ≤15m / s; High wind speed (F high ) is v wind >15m / s;

[0150] Deflection speed fuzzy set: slow (V low ) is v yaw ≤1° / s; medium speed (V medium ) is 1° / s <v yaw ≤3° / s; Fast (V high ) is v yaw >3° / s.

[0151] Use the time series change rate to divide the change period: stable period Δv yaw / Δt<0.5° / s, fast changing period Δv yaw / Δt>=0.5° / s;

[0152] Based on the fuzzy rule definition, if the wind direction is F low And the deflection speed is V low , the system is in a stable period; if the wind direction is F high And the deflection speed is V high , the system is in a period of rapid change;

[0153] Fitting the change relationship of deflection velocity: v yaw =f(θ,v wind ), and the deflection velocity distribution under different wind directions is calculated according to the fitting formula.

[0154] Step 4: Heat treatment control and adaptive adjustment of friction coefficient;

[0155] Assume the target temperature is T target =60℃; the current temperature is T brake =80℃, then the cooling rate r cool = k(T brake -T target ), cooling rate constant k = 0.1, the cooling rate is obtained, and then the process of adaptive adjustment of friction coefficient is:

[0156] Initial friction coefficient l0 = 0.4, temperature correction l = l0 (1-0.01T brake ), when T brake =80℃, then l=0.4(1-0.01·80)=0.08; deflection speed correction: l adjusted =l+0.005v yaw , when v yaw =3° / s, l adjusted =0.08+0.005·3=0.095;

[0157] Based on the simulation results: the time required for the yaw system to recover to the stable period is 15 minutes, and it takes 10 minutes for the system temperature to drop to the target temperature. The friction coefficient and temperature control strategy are adjusted to improve the stability and response efficiency of the yaw system of the wind turbine.

[0158] Therefore, an adaptive adjustment strategy for the friction coefficient of the yaw brake was generated by using the Monte Carlo method and fuzzy mathematics to classify wind direction information, combined with the prediction model and heat treatment instructions. This can effectively respond to the changing needs of the yaw system under different wind directions and wind speeds, and provide theoretical and practical support for the operation optimization of wind turbines.

[0159] Step S4: obtaining wind direction information at the wind turbine in the future period based on big data, matching a calibration scheme from the friction coefficient adaptive adjustment strategy according to the wind direction information, transmitting the calibration scheme to the yaw brake controller, and performing the wind turbine yaw adaptive calibration operation.

[0160] In this embodiment, the wind direction information at the wind turbine in the future period is obtained based on big data, and a calibration scheme is matched from the friction coefficient adaptive adjustment strategy according to the wind direction information, and the calibration scheme is transmitted to the yaw brake controller. When the wind turbine yaw adaptive calibration operation is performed, historical wind direction and wind speed data can be collected to build a big data wind direction database, and a wind direction prediction model (such as based on time series analysis or meteorological model) is used to generate wind direction and wind speed information in the future period. According to the wind direction prediction result, the friction coefficient adaptive adjustment strategy database is queried, and the corresponding calibration scheme is matched from the database. The scheme includes the friction coefficient Adjustment value, yaw brake cooling parameters and yaw speed target; convert the matching calibration scheme into executable control instructions, the instruction content includes the friction coefficient set value, cooling rate parameters and yaw speed adjustment target, transmit the calibration instructions to the yaw brake controller through the communication system, verify the integrity and accuracy of the instruction transmission, and ensure that the controller receives it correctly; the controller adjusts the friction coefficient, yaw brake cooling parameters and yaw speed according to the calibration instructions, monitors the operating status of the yaw system, including yaw speed, brake temperature and actual friction coefficient, compares the actual parameters with the expected values, and verifies the execution effect of the calibration scheme.

[0161] See also Figure 2 The present invention also provides a wind turbine yaw adaptive calibration system based on big data, and the wind turbine yaw adaptive calibration system includes:

[0162] The yaw moment change analysis module 1 is used to generate a brake geometric model based on the yaw brake in combination with the three-dimensional modeling software, and introduce the operating load spectrum into the brake geometric model to analyze the yaw moment change law of the yaw brake;

[0163] The operation cycle acquisition and analysis module 2 is used to analyze the strength limit of the yaw brake according to the yaw moment change law and simulation technology, and analyze the operation cycle of the wind turbine generator set deflection caused by the yaw brake failure based on the strength limit;

[0164] The yaw adjustment strategy generation module 3 is used to predict the change relationship between the wind turbine and the yaw speed and wind direction information through the operation cycle, and generate a friction coefficient adaptive adjustment strategy for the yaw brake according to the change relationship;

[0165] The adaptive calibration operation module 4 is used to obtain the wind direction information at the wind turbine in the future period based on big data, match the calibration scheme from the friction coefficient adaptive adjustment strategy according to the wind direction information, transmit the calibration scheme to the yaw brake controller, and perform the wind turbine yaw adaptive calibration operation.

[0166] In summary, with the help of the above-mentioned technical scheme of the present invention, 1. The present invention analyzes the variation law of the yaw moment based on the yaw brake geometric model and the operating load spectrum, which is helpful to predict the stress state of the wind turbine under different operating conditions, clarify potential problems in design and operation, and analyze the strength limit of the yaw brake and the deflection cycle caused by brake failure to ensure that the yaw brake operates within the safe load range, reduce the risk of equipment damage due to overload, and formulate a more reasonable yaw strategy through deflection cycle prediction, reduce excessive use of the yaw system, and extend the life of the brake. In addition, the adaptive adjustment strategy of the yaw brake friction coefficient can dynamically adapt to different wind conditions, realize precise control of the yaw moment, avoid excessive or small torque, and comprehensively optimize the performance of the yaw system, thereby improving the safety, stability and economic benefits of the wind turbine.

[0167] The present invention uses the yaw moment change law and numerical simulation to accurately quantify the wear value of the yaw brake under different working conditions, and establishes a quantitative relationship between the wear coefficient and the working condition and the yaw moment intensity, quantifies the influence of the working condition and yaw moment on the brake performance, and clarifies the safe operating conditions of the equipment. At the same time, the variable set method is used to calculate the relative ambiguity, obtain the level eigenvalues ​​and explore the influence of the deflection on the eigenvalues, which is convenient for dividing the operating status of the yaw brake and helps the operation and maintenance personnel to grasp the equipment status in real time. Finally, based on the strength limit and the periodic grading strategy, the operation period of the deflection of the yaw brake after the braking failure is predicted, which can realize the early estimation of the deflection period of the wind turbine after the brake failure, and provide a time window for operation and maintenance. The present invention constructs a basic database for wind turbine operation by acquiring historical wind direction information, deflection angle and yaw brake working status data, laying a solid foundation for subsequent analysis, and uses the Monte Carlo method to simulate the uncertainty in complex systems through random sampling, providing a more reliable probability distribution model for the yaw system. At the same time, the wind direction information is classified through fuzzy mathematics to construct a prediction model, revealing the relationship between the deflection speed of the wind turbine and the change of wind direction. Combined with real-time data of wind speed, wind direction and deflection speed, the friction coefficient is controlled through heat treatment, the working state of the yaw brake is optimized, and the mechanical damage caused by excessive or insufficient friction is reduced. Reasonable adjustment of the friction coefficient reduces excessive wear, thereby extending the service life of the yaw brake.

[0168] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0169] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A wind turbine yaw adaptive calibration method based on big data, characterized in that: The wind turbine yaw adaptive calibration method comprises: The brake geometry model is generated based on the combination of the yaw brake and 3D modeling software, and the operating load spectrum is introduced into the brake geometry model to analyze the variation law of the yaw moment of the yaw brake; The strength limit of the yaw brake is analyzed according to the yaw moment variation law and simulation technology, and based on the strength limit, the operation cycle of the wind turbine deflection caused by the yaw brake failure is analyzed; Predict the changing relationship between the wind turbine and the yaw speed and wind direction information through the operation cycle, and generate an adaptive adjustment strategy for the friction coefficient of the yaw brake based on the changing relationship; Based on big data, the wind direction information at the wind turbine in the future period is obtained, and the calibration scheme is matched from the friction coefficient adaptive adjustment strategy according to the wind direction information. The calibration scheme is transmitted to the yaw brake controller to perform the wind turbine yaw adaptive calibration operation.

2. The method for adaptive yaw calibration of a wind turbine generator system based on big data according to claim 1, characterized in that: The method of generating a brake geometric model based on the yaw brake in combination with the three-dimensional modeling software, and introducing the operating load spectrum into the brake geometric model to analyze the variation law of the yaw moment of the yaw brake includes: Obtaining geometric structural parameters of the yaw brake, combining the 3D modeling software with the geometric structural parameters to construct a geometric model of the yaw brake, and introducing the geometric model of the yaw brake into the finite element analysis software to perform assembly adjustment of the geometric model of the yaw brake; Extracting load data of the yaw brake during actual operation based on a data acquisition monitor, and formulating a load spectrum of the yaw brake according to the load data to obtain an operating load spectrum; Define the material properties and contact relationships of the yaw brake geometry model in the finite element analysis software, mesh the yaw brake geometry model, and apply boundary conditions and load information; The operating load spectrum is introduced into the brake geometric model, and the yaw moment of the yaw brake after the load spectrum is applied is calculated using finite element analysis software. After the calculation is completed, the change law of the yaw moment is analyzed.

3. The method for wind turbine yaw adaptive calibration based on big data according to claim 1, characterized in that: The analysis of the strength limit of the yaw brake according to the yaw moment variation law and simulation technology, and the analysis of the operation cycle of the wind turbine generator set deflection caused by the yaw brake failure based on the strength limit include: Based on the variation law of yaw moment, the wear value of yaw brake in yaw process under different working conditions is analyzed by dimensional analysis and numerical simulation technology, and the influence of yaw moment intensity on wear value is analyzed; Establish the wear coefficient based on the impact analysis, determine the quantitative relationship between the wear coefficient and the operating conditions and the yaw moment strength, and use the quantitative relationship to obtain the use strength limit of the yaw brake when operating under the preset conditions; The variable set method is used to calculate the relative fuzziness of the use intensity limit value, obtain the level characteristic value, and use the partial connection coefficient technology to explore the impact of the deflection of the wind turbine on the level characteristic value, and obtain the periodic classification strategy based on the impact results; The operation period of wind turbine deflection after yaw brake failure is estimated based on the use of intensity limit and cycle rating strategy.

4. The method for wind turbine yaw adaptive calibration based on big data according to claim 3, characterized in that: The analysis of the wear value of the yaw brake during the yaw process under different working conditions using dimensional analysis and numerical simulation technology based on the yaw moment change law, and the analysis of the influence of the yaw moment intensity on the wear value include: Based on the variation law of yaw moment and dimensional analysis, the dimensional relationship between the wind wheel, yaw bearing and yaw motor is established, and the dimensionless quantity is set to convert the dimensional relationship into a dimensionless function; The dimensionless function is used to generate the numerical simulation set of the wind rotor, yaw bearing and yaw motor, and the numerical simulation set is combined with the brake geometric model to analyze the yaw drive process under different numerical simulation sets. The working temperature distribution of the yaw drive is analyzed according to the yaw drive process, and the exponential relationship between the yaw moment and the temperature is established based on the working temperature distribution. The exponential relationship is used to determine the wear value of the yaw drive under different working conditions. The wear value is matched with the corresponding yaw moment, the changing relationship between the yaw moment intensity and the wear value is analyzed, and the influence of the yaw moment intensity on the wear value is determined based on the changing relationship.

5. The method for wind turbine yaw adaptive calibration based on big data according to claim 4, characterized in that: The establishment of the wear coefficient according to the impact analysis, the determination of the quantitative relationship between the wear coefficient and the working condition and the yaw moment strength, and the use strength limit of the yaw brake under the preset conditions using the quantitative relationship include: The wear coupling coefficient of the yaw brake is defined based on the influence relationship and the working temperature distribution, and the quality coefficient is set using dimensional technology to analyze the correlation between the wear coupling coefficient and different working conditions. Determine the trend difference between the correlation relationship and the exponential relationship, and determine the coupling constant under different working conditions based on the trend difference results, and determine the quantitative relationship between the wear coefficient and the wear work under different working conditions based on the coupling constant; The quantitative relationship between wear and tear and the coupling constant is combined to determine the quantitative relationship between wear coefficient and yaw moment strength, and the operating conditions of the yaw brake are preset according to the quantitative relationship between wear and tear and the quantitative relationship between yaw moment strength. The operating conditions are used to obtain the usage intensity of the yaw brake during operation, and the corresponding upper and lower strength limits are screened from the usage intensity results to obtain the usage intensity limit.

6. The method for adaptive yaw calibration of a wind turbine generator system based on big data according to claim 5, characterized in that: The variable set method is used to calculate the relative fuzziness of the use intensity limit value, obtain the level characteristic value, and use the partial connection coefficient technology to explore the impact of the deflection of the wind turbine on the level characteristic value. The cycle classification strategy based on the impact result includes: Based on setting the intensity set using the intensity limit, the interval matrix of the upper and lower limits of the intensity is divided according to the intensity set, and the variable set opposition technology is used to search for the gradual change point using the intensity limit in the intensity set; Generate a variable set matrix using the gradually changing metamorphic point and interval matrix, determine the positional relationship of the use intensity limit value in the variable set matrix, and calculate the relative ambiguity of the use intensity limit value based on the positional relationship; According to the relative fuzziness analysis, the strength limit value is used to calculate the total relative fuzziness of the wear coefficient, and the level characteristic values ​​corresponding to different working conditions are calculated based on the total relative fuzziness; The nonlinear relationship between the deflection angle and the level characteristic value is calculated using the partial connection coefficient technology, and the influence of the deflection angle on the level characteristic value is analyzed based on the nonlinear relationship results; Based on the influence relationship, the sensitive interval and threshold between the deflection angle and the level characteristic value are determined, and a periodic grading strategy is generated according to the sensitive interval and threshold.

7. The method for wind turbine yaw adaptive calibration based on big data according to claim 6, characterized in that: The calculation formula of the relative ambiguity is: The calculation formula of the level characteristic value is: In the formula, β represents the relative ambiguity, b ih represents the service strength limit under the i-th working condition, c ij represents the position relationship under the i-th working condition, h ih represents the hth gradual deterioration point under the i-th working condition, δ represents the level characteristic value, h represents the service strength limit, u j (v h ) represents the total relative fuzziness under the jth wear coefficient condition, h i(h+1) It represents the h+1th gradual degradation point under the i-th operating condition.

8. The method for adaptive yaw calibration of a wind turbine generator system based on big data according to claim 1, characterized in that: The method of predicting the changing relationship between the wind turbine and the yaw speed and wind direction information through the operation cycle and generating a friction coefficient adaptive adjustment strategy for the yaw brake according to the changing relationship includes: The wind direction information, deflection angle and working status data of the yaw brake during the historical operation of the wind turbine are obtained by using a data acquisition monitor and combined as the benchmark data; Based on the Monte Carlo method, the benchmark data is extracted to analyze the probability density function of the deflection angle and working status under different wind direction information, and the scale change probability is divided according to the probability density function and Newton's method; According to the scale change probability and fuzzy mathematical theorem, the wind direction information is classified to build a change period prediction model, and the change relationship between the wind turbine and the deflection speed and wind direction information is clarified; According to the changing relationship of the prediction model output during the changing period, the heat treatment control instructions are generated in combination with the deflection speed under different wind speeds and wind directions and the working state of the yaw brake, and the adaptive adjustment strategy of the yaw brake friction coefficient is determined.

9. The method for wind turbine yaw adaptive calibration based on big data according to claim 8, characterized in that: The method of extracting benchmark data based on the Monte Carlo method to analyze the probability density function of the deflection angle and the working state under different wind direction information, and dividing the scale change probability according to the probability density function and the Newton method includes: The deflection angle and working state are set as scale feature and spatial feature respectively, and the Monte Carlo method is used to randomly extract data from the benchmark data to clarify the spatiotemporal distribution of wind direction information. The similarity between the spatiotemporal distribution of wind direction information and the normal distribution is analyzed, and the probability density function is defined based on the similarity results. The root of the probability density function is approximated by using the Newton method. Based on the root results, the change load of the deflection angle and the working state is clarified, and the scale change probability is divided according to the change load results.

10. A wind turbine yaw adaptive calibration system based on big data, used to implement the wind turbine yaw adaptive calibration method based on big data as described in any one of claims 1 to 9, characterized in that: The wind turbine yaw adaptive calibration system includes: The yaw moment change analysis module is used to generate a brake geometry model based on the yaw brake combined with 3D modeling software, and introduce the operating load spectrum into the brake geometry model to analyze the yaw moment change law of the yaw brake; An operation cycle acquisition and analysis module is used to analyze the strength limit of the yaw brake according to the yaw moment change law and simulation technology, and to analyze the operation cycle of the wind turbine deflection caused by the yaw brake failure based on the strength limit; A yaw adjustment strategy generation module is used to predict the changing relationship between the wind turbine and the yaw speed and wind direction information through the operation cycle, and generate a friction coefficient adaptive adjustment strategy for the yaw brake according to the changing relationship; The adaptive calibration operation module is used to obtain the wind direction information at the wind turbine in the future period based on big data, match the calibration plan from the friction coefficient adaptive adjustment strategy according to the wind direction information, transmit the calibration plan to the yaw brake controller, and perform the wind turbine yaw adaptive calibration operation.

Images