An operating analysis method and device for wind turbines

Abstract

The present application discloses an operation analysis method and device for a wind turbine, which relates to the field of electrical digital data processing. The method utilizes the characteristic that there is a linear relationship between the vibration and the power generation of the wind turbine to analyze the operation state of the wind turbine. The relationship between the power generation and the vibration is obtained by linear regression. At the same time, the prediction function of power generation-vibration is also realized through linear regression. Then, by considering the wind speed probability distribution of the wind farm, the power generation that the wind turbine should have is calculated, and the calculated power generation is used as the dependent variable to be substituted into the linear relationship for inversion to obtain the vibration that should be generated. Finally, the data obtained from the forward deduction and the reverse deduction are mutually verified to obtain the outlier data. The outlier is abnormal, and the component corresponding to the marked abnormality is analyzed to obtain the abnormal operation state of the wind turbine.

Description

Technical Field

[0001] The present application relates to the technical field of electric digital data processing, and particularly relates to an operation analysis method and device for a wind turbine. Background Art

[0002] Wind power generation refers to converting the kinetic energy of wind into electrical energy. Wind energy is a clean and pollution-free renewable energy source. Wind power generation drives the rotation of the windmill blades by wind, and then increases the rotation speed through a speed increaser to prompt the generator to generate electricity. Moreover, wind power generation does not require the use of fuel and will not produce radiation or air pollution, making it a renewable new energy source.

[0003] Since the location of the wind farm is relatively remote and the wind turbines operate in the wild for a long time, the complex and changeable environmental conditions pose challenges to the safe and stable operation of the wind turbines. The designed service life of wind turbines is generally about 20 years, but the service life is often shortened due to the damage of some key components. The early abnormal state of the wind turbine often shows through the vibration situation. In the process of converting wind power mechanical energy into electrical energy by the wind turbine unit, many components of the wind turbine unit will generate vibration. When this vibration reaches a certain level or exceeds a certain vibration amplitude, it will lead to a fault, thereby damaging a certain component or even the entire wind turbine unit.

[0004] Due to the continuous construction and operation of wind farms, the number of wind turbines has increased rapidly. Timely and effective operation maintenance and repair of wind turbines is an urgent problem to be solved. Due to the limited number of operation maintenance and repair personnel for wind turbines and the single technical means for monitoring the operation state of wind turbines, the contradiction is prominent, and the risk of wind turbine faults caused by the inability to timely maintain and repair wind turbines increases. Usually, a wind farm will install an alarm system based on a data acquisition and monitoring control system to monitor the operation state of wind turbines. However, since it is an after-fault alarm, the maintenance personnel can only repair the wind turbine after the fault occurs, and it cannot provide the operation state information of the wind turbine for the maintenance personnel. For most wind farms, their maintenance and repair of wind turbines still mostly adopt the methods of regular inspection and after-fault repair to maintain and repair the wind turbines. Due to the shortage of wind turbine repair resources and limited technical conditions, it is difficult to achieve timely repair of wind turbines, resulting in the inability to timely maintain and repair wind turbines during the inspection interval. Only when a wind turbine fails during the inspection interval will it be repaired, which will not only cause maintenance downtime losses but also increase the repair cost of wind turbines. Summary of the Invention

[0005] The main purpose of this application is to provide an operation analysis method, device, equipment and storage medium for wind turbines, so as to solve the problem in the prior art that the operation state of wind turbines is monitored through an alarm system based on a data acquisition and monitoring control system, which is an after-fault alarm. Maintenance personnel can only repair the wind turbines after the faults occur, and cannot provide the operation state information of the wind turbines for maintenance personnel.

[0006] To achieve the above purpose, this application provides the following technical solutions:

[0007] An operation analysis method for wind turbines, the wind turbines include a number of wind turbines located in the same wind farm area, and a vibration detector is respectively installed on each component of each wind turbine. The operation analysis method includes:

[0008] Step S1, based on the current wind turbine, obtain a number of actual vibration data of each component based on a number of preset natural time periods through all vibration detectors;

[0009] Step S2, obtain a number of actual power generation data of the current wind turbine based on a number of preset natural time periods;

[0010] Step S3, define the linear regression relationship between all actual power generation data and the actual vibration data of each component through a multiple linear regression model;

[0011] Step S4, solve the regression coefficients of the linear regression relationship by the least squares method and substitute them into the multiple linear regression model to obtain an analysis model based on the current wind turbine;

[0012] Step S5, obtain a number of wind speed probability distributions of the wind farm area based on a number of preset natural time periods;

[0013] Step S6, calculate the allowable power generation data of each wind turbine based on the wind speed probability distribution of the current preset natural time period;

[0014] Step S7, substitute the allowable power generation data of the current wind turbine into the analysis model for data inversion to obtain the allowable vibration data of all components of the current wind turbine;

[0015] Step S8, based on the current wind turbine, determine whether there are any outlier data among all the allowable vibration data and all the actual vibration data. If there are such outlier data, execute Step S9;

[0016] Step S9, mark the components corresponding to all the outlier data as abnormal operation states.

[0017] As a further improvement of the present application, in step S3, the linear regression relationships between all actual power generation data and the actual vibration data of each component are defined through a multiple linear regression model, including:

[0018] Step S31, define the actual power generation data of the same preset natural time period of the current wind turbine as a dependent variable;

[0019] Step S32, define all the actual vibration data of each component of the same preset natural time period as a set of independent variables;

[0020] Step S33, perform standard normalization processing on the same set of independent variables and dependent variables;

[0021] Step S34, define the linear regression relationship between all dependent variables and all independent variables according to Equation (1):

[0022] (1);

[0023] Wherein, is the dependent variable of the th wind turbine in the th preset natural time period, is the total number of all preset natural time periods, is the intercept of the linear regression relationship, is the linear regression coefficient of the th independent variable, is the total number of independent variables in a set of independent variables, is the th independent variable in the th preset natural time period, is the random error of the linear regression relationship.

[0024] As a further improvement of the present application, in step S4, the regression coefficients of the linear regression relationship are solved by the least squares method and substituted into the multiple linear regression model to obtain an analysis model based on the current wind turbine, including:

[0025] Step S91, define the least squares method by Equation (2) and solve all the regression coefficients in the linear regression relationship of the th wind turbine :

[0026] (2);

[0027] Wherein, is the estimated value of , , is the matrix of all independent variables, ; is the transposed matrix of the matrix .

[0028] Step S92: Substitute all the obtained regression coefficients into the multiple linear regression model to obtain the analysis model of the th wind turbine.

[0029] As a further improvement of this application, in step S5, obtaining several wind speed probability distributions of the wind farm area based on several preset natural time periods includes:

[0030] Step S51: Obtain several actual wind speeds of the wind farm area based on several preset natural time periods through the external anemometers in the wind farm area;

[0031] Step S52: Define the probability distribution function (3) according to the two-parameter Weibull distribution:

[0032] (3);

[0033] where is the probability distribution function, and the value of the probability distribution function is in the interval ; is the scale parameter of the Weibull distribution; is the shape parameter of the Weibull distribution; is the actual wind speed of the current preset natural time period;

[0034] Step S53: Define the probability density function (4) according to the two-parameter Weibull distribution:

[0035] (4);

[0036] where is the probability density function;

[0037] Step S54: Define the log-likelihood function (5) of the scale parameter and the shape parameter:

[0038] (5);

[0039] where is the log-likelihood function;

[0040] Step S55: Solve the scale parameter and the shape parameter based on the log-likelihood function;

[0041] Step S56: Substitute the solved scale parameter and the solved shape parameter into the probability distribution function (3) to obtain the wind speed probability distribution of the current preset natural time period.

[0042] As a further improvement of the present application, in step S6, the promised power generation data of each wind turbine is calculated based on the wind speed probability distribution of the current preset natural time period, including:

[0043] In step S61, the output power relationship of the current wind turbine is defined according to formula (6):

[0044] (6);

[0045] Wherein, is the output power of the wind turbine based on the actual wind speed of the current preset natural time period; is the rated power of the current wind turbine based on the rated wind speed ; is the cut-in wind speed of the current wind turbine; is the cut-out wind speed of the current wind turbine;

[0046] In step S62, obtain the running duration of the current wind turbine running to the current preset natural time period;

[0047] In step S63, obtain the product of the output power of the wind turbine and the running duration, which is the promised power generation data of the current wind turbine.

[0048] As a further improvement of the present application, in step S8, based on the current wind turbine, it is judged whether there are outlier data among all the promised vibration data and all the actual vibration data. If there is such outlier data, then step S9 is executed, including:

[0049] In step S81, integrate all the promised vibration data and all the actual vibration data of the current wind turbine into a comparison data table;

[0050] In step S82, sort all the data in the comparison data table from small to large to obtain an ordered data table;

[0051] In step S83, extract the outliers in the ordered data table by the interquartile range method;

[0052] In step S84, define the outliers as the outlier data.

[0053] As a further improvement of the present application, in step S9, mark the components corresponding to all the outlier data as abnormal operating states, and then, including:

[0054] In step S10, obtain the visual operation style of the wind farm area;

[0055] In step S20, obtain the positions of the wind turbines corresponding to the components marked as the abnormal operating states;

[0056] Step S30, highlight the position of the wind turbine in the visual operation style;

[0057] Step S40, in response to an external touch operation, locally magnify the visual operation style with the position of the wind turbine as the center to obtain a visual magnified operation style;

[0058] Step S50, load and display the component visual styles of all components at the position of the wind turbine in the visual magnified operation style;

[0059] Step S60, highlight the components marked as the abnormal operation state among all component visual styles.

[0060] To achieve the above object, the present application also provides the following technical solutions:

[0061] An operation analysis device for a wind turbine, the operation analysis device is applied to the operation analysis method as described above, and the operation analysis device includes:

[0062] An actual vibration data acquisition module, configured to acquire a plurality of actual vibration data of each component based on a plurality of preset natural time periods through all vibration detection components of the current wind turbine;

[0063] An actual power generation data acquisition module, configured to acquire a plurality of actual power generation data of the current wind turbine based on a plurality of preset natural time periods;

[0064] A linear regression relationship definition module, configured to define the linear regression relationship between all actual power generation data and the actual vibration data of each component through a multiple linear regression model;

[0065] A linear regression relationship solving module, configured to solve the regression coefficients of the linear regression relationship by the least squares method and substitute them into the multiple linear regression model to obtain an analysis model based on the current wind turbine;

[0066] A wind speed probability distribution acquisition module, configured to acquire a plurality of wind speed probability distributions of the wind farm area based on a plurality of preset natural time periods;

[0067] A promised power generation data calculation module, configured to calculate the promised power generation data of each wind turbine based on the wind speed probability distribution of the current preset natural time period;

[0068] A promised vibration data inversion module, configured to substitute the promised power generation data of the current wind turbine into the analysis model for data inversion to obtain the promised vibration data of all components based on the current wind turbine;

[0069] An outlier data judgment module, configured to determine whether there is outlier data in all promised vibration data and all actual vibration data based on the current wind turbine. If there is the outlier data, step S9 is executed;

[0070] An abnormal operation state marking module, configured to mark the components corresponding to all the outlier data as abnormal operation states respectively.

[0071] To achieve the above object, the present application also provides the following technical solutions:

[0072] An electronic device, including a processor and a memory coupled to the processor, where the memory stores program instructions executable by the processor; when the processor executes the program instructions stored in the memory, the above-mentioned operation analysis method for a wind turbine is implemented.

[0073] To achieve the above object, the present application also provides the following technical solutions:

[0074] A storage medium, in which program instructions are stored, and when the program instructions are executed by a processor, the above-mentioned operation analysis method for a wind turbine can be implemented.

[0075] This application is based on the current wind turbine obtaining a number of actual vibration data of each component based on a number of preset natural time periods through all vibration detection components; obtaining a number of actual power generation data of the current wind turbine based on a number of preset natural time periods; defining the linear regression relationship between all actual power generation data and the actual vibration data of each component through a multiple linear regression model; solving the regression coefficients of the linear regression relationship by the least squares method and substituting them into the multiple linear regression model to obtain an analysis model based on the current wind turbine; obtaining a number of wind speed probability distributions of the wind farm area based on a number of preset natural time periods; calculating the allowable power generation data of each wind turbine based on the wind speed probability distribution of the current preset natural time period; substituting the allowable power generation data of the current wind turbine into the analysis model for data inversion to obtain the allowable vibration data of all components based on the current wind turbine; judging whether there are outlier data in all allowable vibration data and all actual vibration data based on the current wind turbine. If there are outlier data, mark the components corresponding to all outlier data as abnormal operating states. This application utilizes the characteristic that there is a linear relationship between the vibration and power generation of the wind turbine to analyze the operating state of the wind turbine. During the operation of the wind turbine, vibration will affect the power generation efficiency of the wind turbine, and thus affect the power generation of the wind turbine. Specifically, during the operation of the wind turbine, vibration will cause wear and fatigue of mechanical components, thereby affecting the overall performance of the wind turbine. Vibration will cause additional stress on key components such as the impeller and bearing of the wind turbine, which may lead to a decrease in efficiency, thus affecting the power generation. And the wear and fatigue of mechanical components will generate abnormal vibration. This application not only solves the relationship between power generation and vibration through linear regression, but also realizes the prediction function of power generation-vibration through linear regression. Then, by considering the wind speed probability distribution of the wind farm, the allowable power generation of the wind turbine is calculated. Then, taking the allowable power generation as the dependent variable and substituting it into the linear relationship for inversion to obtain the vibration that should be generated. Finally, the data obtained from the forward deduction and the reverse deduction are compared with each other to obtain the outlier data. The outlier is abnormal, and marking the component corresponding to the abnormality here analyzes the abnormal operating state of the wind turbine. Description of the Drawings

[0076] Figure 1 It is a schematic flowchart of the steps of an embodiment of an operation analysis method for a wind turbine group according to this application;

[0077] Figure 2 It is a schematic structural diagram of an embodiment of an operation analysis device for a wind turbine group according to this application;

[0078] Figure 3 It is a schematic structural diagram of an embodiment of an electronic device according to this application;

[0079] Figure 4 It is a schematic structural diagram of an embodiment of a storage medium according to this application. Detailed implementation manners

[0080] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present application.

[0081] The terms "first", "second", and "third" in the present application are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first", "second", and "third" may explicitly or implicitly include at least one of such features. In the description of the present application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically and clearly defined. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present application are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0082] Referring to "embodiments" herein means that the specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0083] As Figure 1 shown, this embodiment provides an embodiment of an operation analysis method for a wind turbine. In this embodiment, the wind turbine includes a plurality of wind turbines located in the same wind farm area, and a vibration detection component is respectively installed on each component of each wind turbine.

[0084] For example, a conventional wind turbine generally includes the following components:

[0085] ① Blade: The blade is a key component that captures wind energy and transfers it to the rotor shaft. The design and material of the blade directly affect the performance and power of the wind turbine. The blade materials of modern wind turbines include fiberglass, carbon fiber, etc.

[0086] ② Hub: The hub is the connecting part between the blade and the main shaft, responsible for transferring the forces received by the blade to the transmission system. The design of the hub needs to ensure sufficient strength.

[0087] ③ Main Shaft: The main shaft connects the blade and the generator, transferring the rotational force to the generator.

[0088] ④ Generator: The generator converts mechanical energy into electrical energy. Modern wind turbines usually use induction motors or asynchronous generators, with power ranges from 500 kilowatts to 1500 kilowatts.

[0089] ⑤ Gearbox: The gearbox increases the rotational speed of the low-speed shaft to match the speed requirements of the generator.

[0090] ⑥ Yaw System: The yaw system aligns the nacelle with the wind direction through an electric motor, ensuring that the wind turbine always faces the incoming wind direction.

[0091] ⑦ Control System: The control system monitors the status of the wind turbine and adjusts the rotational speed, voltage, and frequency of the generator as needed to ensure the stable operation of the generator.

[0092] ⑧ Tower: The tower supports the nacelle and the rotor. Generally, the higher the better, because the wind speed is greater at higher altitudes.

[0093] ⑨ Cooling System: The cooling system includes fans and oil cooling elements, which are used to keep the temperatures of the generator and the gearbox within an appropriate range.

[0094] ⑩ Anemometer and Wind Vane: These devices are used to measure the wind speed and direction, helping the control system adjust the direction and power output of the wind turbine.

[0095] For example, some of the above components can reflect some vibration characteristics at the initial stage of a fault. The currently more obvious characteristics are as follows:

[0096] ① Unbalanced rotor mass. The main reasons for causing unbalanced rotor mass are: uneven wear (mainly of the blades) or corrosion of the impeller; uneven dust accumulation or attachments (such as rust) on the blade surface; dust adhesion in the hollow part of the airfoil blade or other cavities; local high temperature of the main shaft causing the shaft to bend; failure to balance the impeller after maintenance; insufficient strength of the impeller resulting in impeller cracking or local deformation; loosening of parts on the impeller or insecure connections.

[0097] The vibration characteristics of rotor mass imbalance are as follows: the vibration value is the largest in the horizontal direction, very small in the axial direction, and the vibration at the bearing seat of the supporting bearing is greater than that at the thrust bearing; the amplitude increases with the increase of the rotation speed; the vibration frequency is equal to the rotation speed frequency; the vibration stability is relatively good and not sensitive to load changes; when there is ash adhesion inside the hollow blade or individual parts are not welded firmly and displaced, the measured phase angle value is unstable, and its vibration frequency is 30% to 50% of the working speed.

[0098] ② Vibration caused by rubbing between stationary and rotating parts. The main reasons for rubbing between stationary and rotating parts are: for example, collision or friction between the outlet of the collector and the inlet of the impeller, collision or friction between the impeller and the casing, and collision or friction between the main shaft and the sealing device.

[0099] The vibration characteristics of rubbing between stationary and rotating parts are: the vibration is unstable; the vibration is self-excited vibration and has nothing to do with the rotation speed; when the rubbing is serious, reverse whirling will occur.

[0100] ③ Vibration caused by abnormal rolling bearings. The main reasons for abnormal rolling bearings are: vibration caused by poor bearing assembly, vibration caused by damage to the surface of the rolling bearing, poor machining of the journal or shaft shoulder, journal bending, bearing installation tilt, the inner ring of the bearing not coinciding with the axis line after assembly, resulting in an alternating axial force acting once per revolution of the bearing, and local vibration caused by the loosening of the fixing round nut of the rolling bearing; due to poor manufacturing quality, poor lubrication, foreign matter entry, and non-standard clearance with the bearing housing of the rolling bearing, wear, corrosion, peeling, and cracking will occur, and after damage, the high-frequency impact vibration generated by the mutual impact of the balls will be transmitted to the bearing seat.

[0101] The vibration characteristics of abnormal rolling bearings are: the vibration value is the largest in the axial direction; the vibration frequency is equal to the rotation frequency; there is a high-frequency impact vibration signal, the vibration stability is very poor, has nothing to do with the load, the amplitude of the vibration may be the largest in all three directions of horizontal, vertical, and axial, and precise diagnosis of the vibration requires the use of spectrum analysis, and spectrum analysis can accurately judge the exact location and degree of damage of the bearing.

[0102] ④ Vibration caused by insufficient stiffness of the bearing seat foundation. The main reasons for insufficient stiffness of the bearing seat foundation are: poor foundation grouting, loose anchor bolts, loose gaskets, and loose connection of the machine base, all of which will cause severe forced resonance phenomena.

[0103] The vibration characteristics of insufficient stiffness of the bearing seat foundation are: the vibration of the bearing seat at the problematic anchor bolt is the largest, and the radial component is the largest; the vibration frequency is a combination of odd multiples of the rotation speed such as 1, 3, 5, 7, etc., and the 3-fold component value is the highest as the frequency domain characteristic of the vibration characteristic.

[0104] ⑤Vibrations caused by abnormal couplings. The main reasons for abnormal couplings are as follows: incorrect coupling installation, misalignment between the fan and motor shafts, and failure to consider the axial displacement compensation amount during alignment of the fan and motor shafts. All of these can cause vibrations in the fan and motor.

[0105] The vibration characteristics of abnormal couplings are as follows: the vibration is irregular, varies significantly with the load, is light during idling and large under full load, and has good vibration stability; the greater the axial deviation, the greater the vibration; when the motor operates alone, the vibration disappears; if the radial vibration is large, the two axis lines are parallel, and if the axial vibration is large, the two axis lines intersect.

[0106] It should be noted that the above vibration characteristics are only for illustrative purposes and do not represent all the vibration characteristics of the wind turbine. Vibration characteristics not listed should also be considered. For example, when there is a turn - to - turn short - circuit in the rotor, there will be many spectra with similar amplitudes, and when there is a turn - to - turn short - circuit in the stator, the amplitude change rule shows a trend of increasing first and then decreasing.

[0107] It is worth noting that the vibration characteristics that have not been clarified need to be explained by the linear regression of this embodiment to show the overall relationship. The above are only examples of some characteristics, and vibrations are often accompanied by resonance of other components, resulting in a high misjudgment rate for single - component vibration detection. However, this defect can be compensated by linear regression.

[0108] Preferably, the operation analysis method includes the following steps:

[0109] Step S1, based on the current wind turbine, obtain a number of actual vibration data of each component based on a number of preset natural time periods through all vibration detection components.

[0110] Preferably, a preset natural time period can be set as a natural day, a natural hour, etc., and can be set according to actual needs.

[0111] Preferably, during the actual application process, when the wind turbine is generating electricity, due to the uncertainty interference of external environmental factors (unstable wind force and direction), the vibration signal of the wind turbine may be missing to varying degrees. Therefore, before detecting the vibration signal of the wind turbine, the signal collected by the vibration sensor can be pre - processed conventionally.

[0112] Specifically, pre - processing can be carried out by removing the trend term and the five - point cubic smoothing method.

[0113] Among them, the detrended term is the vibration signal data collected in the vibration test. Due to the zero drift generated by the amplifier with temperature change, the instability of the low-frequency performance outside the sensor frequency range, and the environmental interference around the sensor, etc., it often deviates from the baseline, and even the magnitude of the deviation from the baseline will change with time. The whole process of the deviation from the baseline changing with time is called the trend term of the signal. The trend term directly affects the correctness of the signal and should be removed. The commonly used method to eliminate the trend term is the polynomial least squares method.

[0114] The detrend() function can be provided in MATLAB for detrending operations, but it can only remove the mean and linear trend terms. Therefore, if this function is used for operations, it is admitted that the trend term contained in the sensor is linear. If the trend term is considered to be non-linear, then a function composed of polyfit() and ployval() needs to be used for operations, such as: Liu_detrend(t,y,m). In the actual processing of vibration signal data, usually a polynomial of degree 1 to 3 is taken to perform polynomial trend term elimination processing on the sampled data.

[0115] Among them, the five-point cubic smoothing method can be used for smoothing processing of time-domain and frequency-domain signals. The main effect of this processing method on time-domain data is to reduce the high-frequency random noise mixed into the vibration signal. And the effect on frequency-domain data is to make the spectral curve smooth, so as to obtain a better fitting effect in modal parameter identification. It should be noted that after the frequency-domain data passes through the five-point cubic smoothing method, the peak value in the spectral curve will decrease and the trapezoid will become wider, which may cause an increase in the error of the identified parameters.

[0116] Step S2, obtain a number of actual power generation data of the current wind turbine based on a number of preset natural time periods.

[0117] Preferably, the actual power generation data of the wind turbine can be directly obtained through the existing monitoring system, and the acquisition method is already a mature existing technology.

[0118] Step S3, define the linear regression relationship between all actual power generation data and the actual vibration data of each component through a multiple linear regression model.

[0119] Preferably, at this time, both the dependent variable and the independent variable of the linear regression relationship are known quantities, and the unknown quantity to be solved is each linear regression coefficient.

[0120] Step S4, solve the regression coefficients of the linear regression relationship by the least squares method and substitute them into the multiple linear regression model to obtain an analysis model based on the current wind turbine.

[0121] Preferably, the least squares method is a mathematical optimization technique that finds the best function match for data by minimizing the sum of the squares of errors. Using the least squares method, unknown data can be easily obtained, and the sum of the squares of the errors between the obtained data and the actual data is minimized.

[0122] Step S5: Obtain the wind speed probability distributions of the wind farm area based on several preset natural time periods.

[0123] Preferably, due to the randomness of wind speed, even if all wind turbines are in the same wind farm, the wind reception conditions of each wind turbine are different, which may lead to different power generation amounts. Therefore, in this embodiment, starting from the wind speed probability distribution is considered to ensure the rationality and accuracy of subsequent data comparison.

[0124] Step S6: Calculate the allowable power generation data of each wind turbine based on the wind speed probability distribution of the current preset natural time period.

[0125] Step S7: Substitute the allowable power generation data of the current wind turbine into the analysis model for data inversion to obtain the allowable vibration data based on all components of the current wind turbine.

[0126] Preferably, at this time, all linear regression coefficients of the linear regression relationship have been solved, that is, the linear regression coefficients are known quantities, and the allowable vibration data becomes an unknown quantity. At this time, substituting the allowable power generation data of the current wind turbine into the analysis model as the dependent variable to solve all independent variables is equivalent to a system of linear equations with multiple variables. As long as the number of non-collinear groups of the system of equations is greater than or equal to the number of variables, all unknown quantities can be solved. At this time, several groups of allowable power generation data are prepared as support for the solution.

[0127] Step S8: Based on the current wind turbine, determine whether there are any outlier data among all the allowable vibration data and all the actual vibration data. If there are outlier data, then execute Step S9.

[0128] Step S9: Mark the components corresponding to all the outlier data as abnormal operating states.

[0129] Preferably, the methods for judging outlier data mainly include the following:

[0130] ① Interquartile range method: IQR = Q3 - Q1, where Q1 is the lower quartile and Q3 is the upper quartile. The upper limit is the maximum value within the non-abnormal range, and the lower limit is the minimum value within the non-abnormal range. If an observed value exceeds this range, it is considered an outlier.

[0131] ②‌The 3σ criterion (the 3-sigma rule)‌: applicable to normally distributed data. First, calculate the mean and standard deviation of the data. Values greater than the mean plus three times the standard deviation or less than the mean minus three times the standard deviation are considered outliers. This method is based on the characteristics of the normal distribution, that is, most of the data (about 99.73%) will fall within three times the standard deviation of the mean.

[0132] ③‌Mahalanobis distance method‌: used to identify outliers in a multi-variable scenario. Mahalanobis distance is a distance measure in a multi-dimensional space. If the Mahalanobis distance of an individual is greater than the critical value, then at the significance level α, this individual can be considered an outlier. Here, the significance level is generally 0.005 or 0.001, and the calculation of the critical value is related to the test standard and degrees of freedom.

[0133] ④‌Median deviation method‌: uses the median to determine outliers. Compared with the mean, the median is not sensitive to extreme values in the data, so it may be more robust in some cases. If the deviation degree of an observed value from the median exceeds a certain threshold, it is considered an outlier.

[0134] ⑤‌Analysis of variance method‌: standardizes the data using analysis of variance, sets the standard deviation as the boundary, and observed values greater than the boundary are considered outliers. After standardizing the data with this method, outliers are determined by comparing the relative magnitudes of the observed values and the standard deviation.

[0135] ⑥‌Range analysis method‌: uses the range between the maximum and minimum values of the data to quantitatively analyze the data. If the deviation degree of an observed value from the maximum or minimum value exceeds a certain threshold calculated based on the range, it is considered an outlier.

[0136] ⑦‌Statistical test method‌: such as Grubbs' Test and Dixon's Test, etc. These methods are based on statistical principles and determine outliers by calculating the statistic and comparing it with the critical value.

[0137] Furthermore, in step S3, define the linear regression relationships between all actual power generation data and the actual vibration data of each component through a multiple linear regression model, including:

[0138] Step S31, define the actual power generation data of the same preset natural time period of the current wind turbine as a dependent variable.

[0139] Step S32, define all the actual vibration data of each component in the same preset natural time period as a set of independent variables.

[0140] Step S33, perform standard normalization processing on the same set of independent and dependent variables.

[0141] Step S34, define the linear regression relationship between all dependent variables and all independent variables according to Equation (1):

[0142] (1).

[0143] Wherein, is the dependent variable of the th wind turbine for the th preset natural time period, is the total number of all preset natural time periods, is the intercept of the linear regression relationship, is the linear regression coefficient of the th independent variable, is the total number of independent variables of a group of independent variables, is the th preset natural time period of the th independent variable, is the random error of the linear regression relationship.

[0144] Preferably, the residual sum of squares of linear regression can be used to judge the fitting effect of the model by comparing its magnitude. The residual sum of squares (RSS) is the sum of the squares of the differences between the actual observed values and the values predicted by the regression equation, and is used to quantify the difference between the predicted value and the actual value of the model.

[0145] Preferably, the judgment criterion for the residual sum of squares is that the smaller the better, that is, the smaller the residual sum of squares, the closer the predicted value of the model is to the actual observed value, and the better the fitting effect of the model; conversely, if the residual sum of squares is large, it indicates that there is a large deviation between the predicted value of the model and the actual observed value, and the fitting effect of the model is poor.

[0146] Furthermore, in step S4, solve the regression coefficients of the linear regression relationship by the least squares method and substitute them into the multiple linear regression model to obtain an analysis model based on the current wind turbine, including:

[0147] Step S91, define the least squares method by Equation (2) and solve all regression coefficients in the linear regression relationship of the th wind turbine :

[0148] (2).

[0149] Wherein, is the estimated value of , , is the matrix of all independent variables, ; is the matrix The transposed matrix.

[0150] Step S92, substitute all the obtained regression coefficients into the multiple linear regression model to obtain the analysis model of the

[0151] th wind turbine.

[0152] Further, in step S5, obtain several wind speed probability distributions of the wind farm area based on several preset natural time periods, including:

[0153] Step S51, obtain several actual wind speeds of the wind farm area based on several preset natural time periods through the external anemometers in the wind farm area.

[0154] (3).

[0155] Where is the probability distribution function, and the value of the probability distribution function is in the interval ; is the scale parameter of the Weibull distribution; is the shape parameter of the Weibull distribution; is the actual wind speed of the current preset natural time period.

[0156] Step S53, define the probability density function (4) according to the two-parameter Weibull distribution:

[0157] (4).

[0158] Where is the probability density function.

[0159] Step S54, define the log-likelihood function (5) of the scale parameter and the shape parameter:

[0160] (5).

[0161] Where is the log-likelihood function.

[0162] Preferably, this embodiment provides a solution process for the log-likelihood function:

[0163] Suppose: and , then:

[0164] .

[0165] Modify the above formula to obtain the matrix equation:

[0166] .

[0167] Iterate the above matrix equation by the Jacobi iteration method until the spectral radius of the matrix equation When, it is determined to converge.

[0168] After convergence, the scale parameter and shape parameter of the Weibull distribution can be obtained.

[0169] Step S55, solve the scale parameter and shape parameter based on the log-likelihood function.

[0170] Step S56, substitute the solved scale parameter and the solved shape parameter into the probability distribution function (3) to obtain the wind speed probability distribution of the current preset natural time period.

[0171] Furthermore, in step S6, calculate the promised power generation data of each wind turbine based on the wind speed probability distribution of the current preset natural time period, including:

[0172] Step S61, define the output power relationship of the current wind turbine according to formula (6):

[0173] (6).

[0174] Among them, is the output power of the wind turbine based on the actual wind speed of the current preset natural time period; is the rated power of the current wind turbine based on the rated wind speed ; is the cut-in wind speed of the current wind turbine; is the cut-out wind speed of the current wind turbine.

[0175] Step S62, obtain the running duration of the current wind turbine running to the current preset natural time period.

[0176] Step S63, obtain the product of the wind turbine output power and the running duration as the promised power generation data of the current wind turbine.

[0177] Furthermore, in step S8, based on the current wind turbine, determine whether there are any outlier data in all the promised vibration data and all the actual vibration data. If there are outlier data, then execute step S9, including:

[0178] Step S81, integrate all the promised vibration data and all the actual vibration data of the current wind turbine into a comparison data table.

[0179] Step S82, sort all the data in the comparison data table from smallest to largest to obtain an ordered data table.

[0180] Step S83, extract the outliers in the ordered data table by the interquartile range method.

[0181] Step S84, define the outlier as the outlier data.

[0182] Preferably, in this embodiment, the interquartile range method is preferably used to calculate the outlier data. The calculation method of the interquartile range (IQR) is to subtract the first quartile (Q1) from the third quartile (Q3) of the data set, that is: IQR = Q3 - Q1. The specific calculation steps are as follows:

[0183] Data sorting: Sort the data set according to the numerical size.

[0184] Calculate Q1: Find the position of the 25% data points in the data set, and the data value at this position is the first quartile (Q1). If the data volume is odd, Q1 is the number before the middle two numbers; if the data volume is even, Q1 is the average of the middle two numbers.

[0185] Calculate Q3: Find the position of the 75% data points in the data set, and the data value at this position is the third quartile (Q3). Similarly, if the data volume is odd, Q3 is the number after the middle two numbers; if the data volume is even, Q3 is also the average of the middle two numbers, but this time it is the two numbers at the back.

[0186] Calculate IQR: Calculate the interquartile range using the formula IQR = Q3 - Q1.

[0187] The interquartile range reflects the dispersion degree of the middle 50% of the data. The smaller the value, the more concentrated the middle data; the larger the value, the more dispersed the middle data. The interquartile range is not affected by extreme values and is a robust method for measuring the dispersion degree of data in descriptive statistics.

[0188] Further, in step S9, mark all the components corresponding to the outlier data as the abnormal operation state. After that, it includes:

[0189] Step S10, obtain the visual operation style of the wind farm area.

[0190] Step S20, obtain the position of the wind turbine corresponding to the component marked as the abnormal operation state.

[0191] Step S30, highlight the position of the wind turbine in the visual operation style.

[0192] Step S40, in response to an external touch operation, locally magnify the visual operation style centered on the position of the wind turbine to obtain a visually magnified operation style.

[0193] Step S50: Load and display the component visualization styles of all components at the position of the wind turbine with the visualized enlarged operation style.

[0194] Step S60: Highlight the components marked as abnormal operation status in all component visualization styles.

[0195] Preferably, in this embodiment, the abnormal components and abnormal wind turbines are visualized to further improve the user experience.

[0196] In this embodiment, based on the current wind turbine, a plurality of actual vibration data of each component based on a plurality of preset natural time periods are obtained through all vibration detection components; a plurality of actual power generation data of the current wind turbine based on a plurality of preset natural time periods are obtained; the linear regression relationships between all the actual power generation data and the actual vibration data of each component are defined through a multiple linear regression model; the regression coefficients of the linear regression relationships are solved by the least squares method and substituted into the multiple linear regression model to obtain an analysis model based on the current wind turbine; a plurality of wind speed probability distributions of the wind farm area based on a plurality of preset natural time periods are obtained; the allowable power generation data of each wind turbine are calculated respectively based on the wind speed probability distribution of the current preset natural time period; the allowable power generation data of the current wind turbine are substituted into the analysis model for data inversion to obtain the allowable vibration data of all components based on the current wind turbine; based on the current wind turbine, it is judged whether there are outlier data among all the allowable vibration data and all the actual vibration data. If there are outlier data, the components corresponding to all the outlier data are marked as abnormal operation status. This embodiment utilizes the characteristic that there is a linear relationship between the vibration and power generation of the wind turbine to analyze the operation status of the wind turbine. During the operation of the wind turbine, vibration will affect the power generation efficiency of the wind turbine, and thus affect the power generation of the wind turbine. Specifically, during the operation of the wind turbine, vibration will cause wear and fatigue of mechanical components, and thus affect the overall performance of the wind turbine. Vibration will cause additional stress on key components such as the impeller and bearing of the wind turbine, which may lead to a decrease in efficiency, thereby affecting the power generation. And the wear and fatigue of mechanical components will all generate abnormal vibrations. This embodiment not only solves the relationship between power generation and vibration through linear regression, but also realizes the prediction function of power generation-vibration through linear regression. Then, by considering the wind speed probability distribution of this wind farm, the power generation that the wind turbine should have is calculated, and then the power generation that should be generated is used as the dependent variable to substitute into the linear relationship for inversion to obtain the vibration that should be generated. Finally, the data obtained from the forward deduction and the reverse deduction are compared with each other to obtain the outlier data. The outlier is abnormal, and the component corresponding to the marked abnormality is analyzed to obtain the abnormal operation status of the wind turbine.

[0197] Such as Figure 2As shown in the figure, this embodiment provides an embodiment of an operation analysis device for a wind turbine. In this embodiment, the operation analysis device is applied to the operation analysis method in the above embodiment.

[0198] Specifically, the operation analysis device includes an actual vibration data acquisition module 1, an actual power generation data acquisition module 2, a linear regression relationship definition module 3, a linear regression relationship solving module 4, a wind speed probability distribution acquisition module 5, a promised power generation data calculation module 6, a promised vibration data inversion module 7, an outlier data judgment module 8, and an abnormal operation state marking module 9, which are electrically connected in sequence.

[0199] Among them, the actual vibration data acquisition module 1 is used to obtain a plurality of actual vibration data of each component based on a plurality of preset natural time periods through all vibration detection components of the current wind turbine; the actual power generation data acquisition module 2 is used to obtain a plurality of actual power generation data of the current wind turbine based on a plurality of preset natural time periods; the linear regression relationship definition module 3 is used to define the linear regression relationship between all actual power generation data and the actual vibration data of each component through a multiple linear regression model; the linear regression relationship solving module 4 is used to solve the regression coefficients of the linear regression relationship by the least squares method and substitute them into the multiple linear regression model to obtain an analysis model based on the current wind turbine; the wind speed probability distribution acquisition module 5 is used to obtain a plurality of wind speed probability distributions of the wind farm area based on a plurality of preset natural time periods; the promised power generation data calculation module 6 is used to calculate the promised power generation data of each wind turbine based on the wind speed probability distribution of the current preset natural time period; the promised vibration data inversion module 7 is used to substitute the promised power generation data of the current wind turbine into the analysis model for data inversion to obtain the promised vibration data of all components of the current wind turbine; the outlier data judgment module 8 is used to judge whether there is outlier data among all the promised vibration data and all the actual vibration data based on the current wind turbine; the abnormal operation state marking module 9 is used to mark the components corresponding to all the outlier data as abnormal operation states if there is outlier data.

[0200] Furthermore, the linear regression relationship definition module 3 specifically includes a first linear regression relationship definition sub-module, a second linear regression relationship definition sub-module, a third linear regression relationship definition sub-module, and a fourth linear regression relationship definition sub-module, which are electrically connected in sequence; the first linear regression relationship definition sub-module is electrically connected to the actual power generation data acquisition module 2, and the fourth linear regression relationship definition sub-module is electrically connected to the linear regression relationship solving module 4.

[0201] Among them, the first linear regression relationship definition sub-module is used to define the actual power generation data of the same preset natural time period of the current wind turbine as a dependent variable; the second linear regression relationship definition sub-module is used to define all the actual vibration data of each component in the same preset natural time period as a set of independent variables; the third linear regression relationship definition sub-module is used to perform standard normalization processing on the same set of independent and dependent variables; the fourth linear regression relationship definition sub-module is used to define the linear regression relationship between all dependent variables and all independent variables according to Equation (1):

[0202] (1).

[0203] Among them, is the dependent variable of the th wind turbine in the th preset natural time period, is the total number of all preset natural time periods, is the intercept of the linear regression relationship, is the th linear regression coefficient of the independent variable, is the total number of independent variables in a set of independent variables, is the th independent variable in the th preset natural time period, is the random error of the linear regression relationship.

[0204] Furthermore, the linear regression relationship solving module 4 specifically includes a first linear regression relationship solving sub-module and a second linear regression relationship solving sub-module that are electrically connected in sequence; the first linear regression relationship solving sub-module is electrically connected to the fourth linear regression relationship definition sub-module, and the second linear regression relationship solving sub-module is electrically connected to the wind speed probability distribution obtaining module 5.

[0205] Among them, the first linear regression relationship solving sub-module is used to define the least squares method through Equation (2) and solve all the regression coefficients in the linear regression relationship of the th wind turbine :

[0206] (2).

[0207] Among them, is the estimated value of, , is the matrix of all independent variables, ; is the transposed matrix of the matrix .

[0208] The second linear regression relationship solving sub-module is used to substitute all the obtained regression coefficients into the multiple linear regression model to obtain the analysis model of the th wind turbine.

[0209] Furthermore, the wind speed probability distribution obtaining module 5 specifically includes a first wind speed probability distribution obtaining sub-module, a second wind speed probability distribution obtaining sub-module, a third wind speed probability distribution obtaining sub-module, a fourth wind speed probability distribution obtaining sub-module, a fifth wind speed probability distribution obtaining sub-module, and a sixth wind speed probability distribution obtaining sub-module that are electrically connected in sequence; the first wind speed probability distribution obtaining sub-module is electrically connected to the second linear regression relationship solving sub-module, and the sixth wind speed probability distribution obtaining sub-module is electrically connected to the promised power generation data calculation module 6.

[0210] Among them, the first wind speed probability distribution obtaining sub-module is used to obtain a number of actual wind speeds of the wind farm area based on a number of preset natural time periods through the external anemometers in the wind farm area.

[0211] The second wind speed probability distribution obtaining sub-module is used to define the probability distribution function (3) according to the two-parameter Weibull distribution:

[0212] (3).

[0213] Among them, is the probability distribution function, and the value of the probability distribution function is in the interval ; is the scale parameter of the Weibull distribution; is the shape parameter of the Weibull distribution; is the actual wind speed of the current preset natural time period.

[0214] The third wind speed probability distribution obtaining sub-module is used to define the probability density function (4) according to the two-parameter Weibull distribution:

[0215] (4).

[0216] Among them, is the probability density function.

[0217] The fourth wind speed probability distribution obtaining sub-module is used to define the logarithmic likelihood function (5) of the scale parameter and the shape parameter:

[0218] (5).

[0219] Among them, is the logarithmic likelihood function.

[0220] The fifth wind speed probability distribution obtaining sub-module is used to solve the scale parameter and the shape parameter based on the logarithmic likelihood function.

[0221] The sixth wind speed probability distribution obtaining sub-module is used to substitute the solved scale parameter and the solved shape parameter into the probability distribution function (3) to obtain the wind speed probability distribution of the current preset natural time period.

[0222] Further, the promised power generation data calculation module 6 specifically includes a first promised power generation data calculation sub-module, a second promised power generation data calculation sub-module, and a third promised power generation data calculation sub-module that are electrically connected in sequence; the first promised power generation data calculation sub-module is electrically connected to the sixth wind speed probability distribution obtaining sub-module, and the third promised power generation data calculation sub-module is electrically connected to the promised vibration data inversion module 7.

[0223] Among them, the first promised power generation data calculation sub-module is used to define the output power relationship formula of the current wind turbine according to formula (6):

[0224] (6).

[0225] Among them, is the output power of the wind turbine based on the actual wind speed of the current preset natural time period; is the rated power of the current wind turbine based on the rated wind speed ; is the cut-in wind speed of the current wind turbine; is the cut-out wind speed of the current wind turbine.

[0226] The second promised power generation data calculation sub-module is used to obtain the operation duration of the current wind turbine running to the current preset natural time period.

[0227] The third promised power generation data calculation sub-module is used to obtain the product of the wind turbine output power and the operation duration, which is the promised power generation data of the current wind turbine.

[0228] Further, the outlier data judgment module 8 specifically includes a first outlier data judgment sub-module, a second outlier data judgment sub-module, a third outlier data judgment sub-module, and a fourth outlier data judgment sub-module that are electrically connected in sequence; the first outlier data judgment sub-module is electrically connected to the promised vibration data inversion module 7, and the fourth outlier data judgment sub-module is electrically connected to the abnormal operation state marking module 9.

[0229] Among them, the first outlier data judgment sub-module is used to integrate all the promised vibration data and all the actual vibration data of the current wind turbine into a comparison data table; the second outlier data judgment sub-module is used to sort all the data in the comparison data table from small to large to obtain an ordered data table; the third outlier data judgment sub-module is used to extract the outliers in the ordered data table by the interquartile range method; the fourth outlier data judgment sub-module is used to define the outliers as outlier data.

[0230] Furthermore, the operation analysis device further includes a wind farm operation pattern visualization module, an abnormal wind turbine position acquisition module, an abnormal wind turbine position highlighting module, an abnormal wind turbine position touch module, a component visualization module, and an abnormal component highlighting module, which are electrically connected in sequence; the wind farm operation pattern visualization module is electrically connected to the abnormal operation state marking module 9.

[0231] Among them, the wind farm operation pattern visualization module is used to obtain the visual operation pattern of the wind farm area; the abnormal wind turbine position acquisition module is used to obtain the wind turbine position corresponding to the component marked as an abnormal operation state; the abnormal wind turbine position highlighting module is used to highlight the wind turbine position in the visual operation pattern; the abnormal wind turbine position touch module is used to respond to an external touch operation to locally magnify the visual operation pattern centered on the wind turbine position to obtain a visual magnified operation pattern; the component visualization module is used to load and display the component visualization styles of all components at the wind turbine position in the visual magnified operation pattern; the abnormal component highlighting module is used to highlight the components marked as abnormal operation states in all component visualization styles.

[0232] It should be noted that this embodiment is a functional module embodiment based on the above method embodiment. For the preferred, extended, limited, exemplified, and principle description parts of this embodiment, refer to the above embodiment, and this embodiment will not be elaborated here.

[0233] In this embodiment, based on the current wind turbine, a plurality of actual vibration data of each component based on a plurality of preset natural time periods are obtained through all vibration detection components; a plurality of actual power generation data of the current wind turbine based on a plurality of preset natural time periods are obtained; a linear regression relationship between all the actual power generation data and the actual vibration data of each component is defined through a multiple linear regression model; the regression coefficients of the linear regression relationship are solved by the least squares method and substituted into the multiple linear regression model to obtain an analysis model based on the current wind turbine; a plurality of wind speed probability distributions of the wind farm area based on a plurality of preset natural time periods are obtained; the allowable power generation data of each wind turbine are calculated respectively based on the wind speed probability distribution of the current preset natural time period; the allowable power generation data of the current wind turbine are substituted into the analysis model for data inversion to obtain the allowable vibration data of all components based on the current wind turbine; based on the current wind turbine, it is judged whether there are outlier data among all the allowable vibration data and all the actual vibration data. If there are outlier data, the components corresponding to all the outlier data are marked as abnormal operating states. This embodiment utilizes the characteristic that there is a linear relationship between the vibration and power generation of the wind turbine to analyze the operating state of the wind turbine. During the operation of the wind turbine, vibration will affect the power generation efficiency of the wind turbine, and thus affect the power generation of the wind turbine. Specifically, during the operation of the wind turbine, vibration will cause wear and fatigue of mechanical components, thereby affecting the overall performance of the wind turbine. Vibration will cause additional stress on key components such as the impeller and bearing of the fan, which may lead to a decrease in efficiency, thus affecting the power generation. And the wear and fatigue of mechanical components will generate abnormal vibration. This embodiment not only solves the relationship between power generation and vibration through linear regression, but also realizes the prediction function of power generation-vibration through linear regression. Then, by considering the wind speed probability distribution of the wind farm, the power generation that the wind turbine should have is calculated. Then, the power generation that should have is used as the dependent variable to perform inversion in the linear relationship to obtain the vibration that should be generated. Finally, the data obtained from the forward deduction and the reverse deduction are compared with each other to obtain the outlier data. The outlier is abnormal, and marking the component corresponding to the abnormality here analyzes the abnormal operating state of the wind turbine.

[0234] Figure 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As Figure 3 shown, the electronic device 10 includes a processor 101 and a memory 102 coupled to the processor 101.

[0235] The memory 102 stores program instructions for implementing a method for analyzing the operation of a wind turbine group according to any one of the above embodiments.

[0236] The processor 101 is configured to execute the program instructions stored in the memory 102 to perform analysis on the operation of the wind turbine group.

[0237] Among them, the processor 101 can also be referred to as a CPU (Central Processing Unit). The processor 101 may be an integrated circuit chip with signal processing capabilities. The processor 101 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0238] Furthermore, Figure 4 is a schematic structural diagram of a storage medium according to an embodiment of the present application. Refer to Figure 4 , the storage medium 11 of the embodiment of the present application stores program instructions 111 that can implement all the above methods. Among them, the program instructions 111 can be stored in the above storage medium in the form of a software product, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, or terminal devices such as computers, servers, mobile phones, and tablets.

[0239] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, indirect couplings or communication connections of devices or units, and can be in electrical, mechanical, or other forms.

[0240] In addition, each functional unit in various embodiments of the present application may be integrated into one processing unit, may exist separately as individual physical units, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software functional units. The above is only the implementation manner of the present application, and does not limit the patent scope of the present application. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. An operation analysis method for a wind turbine generator set, the wind turbine generator set comprising a plurality of wind turbines located within the same wind farm area, and a vibration detector being respectively installed on each component of each wind turbine, characterized in that, The described operation analysis method includes: Step S1: Based on the current wind turbine, obtain a number of actual vibration data of each component based on a number of preset natural time periods through all vibration detectors; Step S2: Obtain a number of actual power generation data of the current wind turbine based on a number of preset natural time periods; Step S3: Define the linear regression relationships between all the actual power generation data and the actual vibration data of each component through a multiple linear regression model; Step S4: Solve the regression coefficients of the linear regression relationship by the least squares method and substitute them into the multiple linear regression model to obtain an analysis model based on the current wind turbine; Step S5: Obtain a number of wind speed probability distributions of the wind farm area based on a number of preset natural time periods; Step S6: Calculate the allowable power generation data of each wind turbine respectively based on the wind speed probability distribution of the current preset natural time period; Step S7: Substitute the allowable power generation data of the current wind turbine into the analysis model for data inversion to obtain the allowable vibration data of all components based on the current wind turbine; Step S8: Based on the current wind turbine, determine whether there are outlier data among all the allowable vibration data and all the actual vibration data. If there are such outlier data, execute Step S9; Step S9: Mark the components corresponding to all the outlier data as abnormal operating states; Step S8: Based on the current wind turbine, determine whether there are outlier data among all the allowable vibration data and all the actual vibration data. If there are such outlier data, execute Step S9, including: Step S81: Integrate all the allowable vibration data and all the actual vibration data of the current wind turbine into a comparison data table; Step S82: Sort all the data in the comparison data table from smallest to largest to obtain an ordered data table; Step S83: Extract the outliers in the ordered data table by the interquartile range method; Step S84: Define the outliers as the outlier data; Step S9: Mark the components corresponding to all the outlier data as abnormal operating states. After that, it includes: Step S10: Obtain the visual operation style of the wind farm area; Step S20: Obtain the positions of the wind turbines corresponding to the components marked as the abnormal operating states; Step S30: Highlight the positions of the wind turbines in the visual operation style; Step S40: In response to an external touch operation, locally magnify the visual operation style with the position of the wind turbine as the center to obtain a visually magnified operation style; Step S50: Load and display the component visual styles of all components at the position of the wind turbine in the visually magnified operation style; Step S60: Highlight the components marked as the abnormal operating states in all the component visual styles; 2. The operation analysis method according to claim 1, wherein Step S3: Define the linear regression relationships between all the actual power generation data and the actual vibration data of each component through a multiple linear regression model, including: Step S31: Based on the current wind turbine, define the actual power generation data of the same preset natural time period as a dependent variable; Step S32: Define all the actual vibration data of each component within the same preset natural time period as a set of independent variables; Step S33: Perform standard normalization processing on the same set of independent variables and dependent variables; Step S34: Define the linear regression relationship between all the dependent variables and all the independent variables according to Equation (1): （1）； wherein, is the dependent variable of the th wind turbine for the th preset natural time period, is the total number of all preset natural time periods, is the intercept of the linear regression relationship, is the linear regression coefficient of the th independent variable, is the total number of independent variables of a group of independent variables, is the th independent variable of the th preset natural time period, is the random error of the linear regression relationship.

3. The operation analysis method according to claim 2, wherein Step S4: Solve the regression coefficients of the linear regression relationship by the least squares method and substitute them into the multiple linear regression model to obtain an analysis model based on the current wind turbine, including: Step S91, define the least squares method by formula (2) and solve all regression coefficients in the linear regression relationship of the th wind turbine : （2）； wherein, is the estimated value of, , is the matrix of all independent variables, ; is the transposed matrix of the matrix ; Step S92, substitute all the obtained regression coefficients into the multiple linear regression model to obtain the analysis model of the th wind turbine.

4. The operation analysis method according to claim 1, wherein Step S5: Obtain the wind speed probability distributions of the wind farm area based on several preset natural time periods, including: Step S51: Obtain several actual wind speeds of the wind farm area based on several preset natural time periods through the external anemometers within the wind farm area; Step S52: Define the probability distribution function (3) according to the two-parameter Weibull distribution: （3）； Among them, is the probability distribution function, and the value of the probability distribution function is in the interval ; is the scale parameter of the Weibull distribution; is the shape parameter of the Weibull distribution; is the actual wind speed of the current preset natural time period; Step S53: Define the probability density function (4) according to the two-parameter Weibull distribution: （4）； wherein, is the probability density function; Step S54: Define the logarithmic likelihood function (5) of the scale parameter and the shape parameter: （5）； Among them, is the log-likelihood function; Step S55: Solve the scale parameter and the shape parameter based on the logarithmic likelihood function; Step S56: Substitute the solved scale parameter and the solved shape parameter into the probability distribution function (3) to obtain the wind speed probability distribution of the current preset natural time period.

5. The operation analysis method according to claim 4, wherein Step S6: Calculate the promised power generation data of each wind turbine respectively based on the wind speed probability distribution of the current preset natural time period, including: Step S61: Define the output power relationship formula of the current wind turbine according to Equation (6): （6）； Among them, is the output power of the wind turbine based on the actual wind speed in the current preset natural time period; is the rated power of the current wind turbine based on the rated wind speed ; is the cut-in wind speed of the current wind turbine; is the cut-out wind speed of the current wind turbine; Step S62: Obtain the operation duration of the current wind turbine running to the current preset natural time period; Step S63: Obtain the product of the output power of the wind turbine and the operation duration, which is the promised power generation data of the current wind turbine.

6. An operation analysis device for a wind turbine, the operation analysis device being applied to the operation analysis method according to any one of claims 1 to 5, characterized in that The operation analysis device includes: An actual vibration data acquisition module, configured to acquire several actual vibration data of each component based on several preset natural time periods through all vibration detectors based on the current wind turbine; An actual power generation data acquisition module, configured to acquire several actual power generation data of the current wind turbine based on several preset natural time periods; A linear regression relationship definition module, configured to define the linear regression relationship between all the actual power generation data and the actual vibration data of each component through a multiple linear regression model; A linear regression relationship solving module, configured to solve the regression coefficients of the linear regression relationship by the least squares method and substitute them into the multiple linear regression model to obtain an analysis model based on the current wind turbine; A wind speed probability distribution acquisition module, configured to acquire the wind speed probability distributions of the wind farm area based on several preset natural time periods; A promised power generation data calculation module, configured to calculate the promised power generation data of each wind turbine respectively based on the wind speed probability distribution of the current preset natural time period; A promised vibration data inversion module, configured to substitute the promised power generation data of the current wind turbine into the analysis model for data inversion to obtain the promised vibration data of all components based on the current wind turbine; An outlier data judgment module, which is used to judge whether there is outlier data in all promised vibration data and all actual vibration data based on the current wind turbine. If there is such outlier data, step S9 is executed; An abnormal operation state marking module, which is used to mark the components corresponding to all outlier data as abnormal operation states.

7. An electronic device, characterized in that, It includes a processor and a memory coupled to the processor. The memory stores program instructions executable by the processor. When the processor executes the program instructions stored in the memory, it implements an operation analysis method according to any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium stores program instructions, and when the program instructions are executed by a processor, an operation analysis method according to any one of claims 1 to 5 can be implemented.

Images