A method and related device for diagnosing wind turbine rotor imbalance faults

Abstract

This invention discloses a method and related apparatus for diagnosing wind turbine rotor imbalance faults. The method includes acquiring the rotor frequency amplitude within a preset period while the wind turbine is in grid-connected power generation mode and sequentially placing it into a rotor imbalance trend verification array. When the preset period is greater than a long-term threshold for rotor imbalance trend, and the suspected abnormality condition for rotor imbalance trend is met, a trend verification method is used to diagnose long-term abnormality faults in rotor imbalance trend. When the preset period is less than a short-term threshold for rotor imbalance trend, a cumulative deviation curve of rotor frequency amplitude is plotted based on the cumulative deviation of each rotor frequency amplitude relative to the historical rotor frequency target amplitude to diagnose short-term abnormality faults in rotor imbalance trend. This invention can capture both long-term trend enhancement characteristics and remain sensitive to sudden anomalies, effectively avoiding delayed or missed early fault reporting.

Description

Technical Field

[0001] This invention relates to the field of wind power technology, and more specifically, to a method and related apparatus for diagnosing wind turbine rotor imbalance faults. Background Technology

[0002] Wind power, as a clean energy technology, plays a vital role in the global energy structure transformation. Wind turbines (or simply "wind turbines") are core equipment, and their operational reliability and stability directly affect the power generation efficiency and economic benefits of wind farms. During wind turbine operation, rotor imbalance is a common fault, posing a serious threat to the safety and lifespan of the equipment. When rotor imbalance develops to the middle or late stages, the vibration of key components such as blades, towers, yaw mechanisms, and main shafts intensifies, increasing fatigue loads and leading to a decrease in operational lifespan. In severe cases, extreme accidents such as blade breakage or tower collapse may occur.

[0003] Currently, the common method for diagnosing wind turbine rotor imbalance faults is static threshold diagnosis based on the analysis of nacelle vibration characteristics, which relies heavily on monitoring the amplitude of the rotor frequency (1P) in the nacelle vibration signal. However, wind turbine blades are prone to structural damage such as bulging, delamination, and cracking under long-term complex loads. Because these types of damage are small in the early stages of degradation, and the rotor frequency amplitude fluctuates due to changes in wind speed, yaw, pitch control strategies, and other operating conditions, they are difficult to effectively identify using ordinary vibration alarms or fixed fault thresholds.

[0004] Traditional diagnostic methods based on static thresholds are only applicable to the stage when the wind turbine imbalance fault has developed to the middle and late stages, resulting in a significant increase in the nacelle vibration signal. Therefore, there is an unavoidable risk of missed or delayed reporting of early wind turbine imbalance faults. Summary of the Invention

[0005] In view of this, the present invention discloses a method and related device for diagnosing wind turbine rotor imbalance faults, so as to effectively avoid the delayed reporting and missed reporting of early faults and significantly improve the ability to detect wind turbine rotor imbalance faults in advance.

[0006] A method for diagnosing wind turbine rotor imbalance faults includes:

[0007] When the wind turbine is in grid-connected power generation state, the wind turbine frequency amplitude within a preset period is obtained, and each wind turbine frequency amplitude is sequentially placed into the wind turbine imbalance change trend test array according to the time sequence.

[0008] It is determined whether the preset period is greater than the long-period threshold of the wind turbine imbalance change trend or less than the short-period threshold of the wind turbine imbalance change trend.

[0009] If the preset period is greater than the long period threshold of the wind turbine imbalance change trend, and the wind turbine frequency amplitude in the wind turbine imbalance change trend test array meets the suspected abnormal wind turbine imbalance change trend condition, the trend test method is used to perform long-term fault diagnosis of the wind turbine imbalance change trend abnormality in the wind turbine imbalance change trend test array.

[0010] If the preset period is less than the short-period threshold of the wind turbine imbalance change trend, the cumulative deviation of each wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude is calculated sequentially according to the time sequence of each wind turbine frequency amplitude in the wind turbine imbalance change trend test array, and a wind turbine frequency amplitude cumulative deviation curve is plotted. The abnormal short-term fault diagnosis of the wind turbine imbalance change trend is performed based on the changing trend of the wind turbine frequency amplitude cumulative deviation curve. Each cumulative deviation is the sum of the deviation of the current time sequence wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude and the cumulative deviation of the previous time sequence wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude.

[0011] Optionally, obtaining the wind turbine rotation frequency amplitude within a preset period includes:

[0012] When the wind turbine operating state characteristics under any sliding window within the preset period meet the following judgment conditions, the wind turbine rotation frequency amplitude value corresponding to the sliding window is obtained, and the judgment conditions include:

[0013] The standard deviation of the wind turbine speed is less than the threshold for judging the stability of the wind turbine speed.

[0014] The absolute value of the difference between the wind turbine frequency and the tower's first-order frequency is greater than the frequency difference threshold, which is determined based on the frequency deviation adjustment coefficient.

[0015] The turbulence intensity did not exceed the turbulence intensity threshold.

[0016] The operating characteristics of the wind turbine include: the standard deviation of the wind turbine rotation speed, the wind turbine rotation frequency, and the turbulence intensity.

[0017] Optionally, the process of determining the operating state characteristics of the wind turbine under any sliding window includes:

[0018] Based on the wind turbine rotor speed of the wind turbine, determine the standard deviation and average value of the wind turbine rotor speed within a preset time period;

[0019] The wind turbine frequency is calculated based on the average wind turbine rotation speed.

[0020] A wind turbine frequency identification frequency range is found within a preset range of the calculated wind turbine frequency value. The maximum amplitude value is found in the range corresponding to the wind turbine frequency identification frequency range in the nacelle vibration signal spectrum as the final identified wind turbine frequency amplitude value. The frequency value corresponding to the maximum amplitude value in the nacelle vibration signal spectrum is taken as the final identified wind turbine frequency. The nacelle vibration signal spectrum is obtained by performing a fast Fourier transform on the nacelle vibration signal.

[0021] The turbulence intensity within the preset time period is determined based on the wind speed of the wind turbine.

[0022] Optionally, the process for determining whether the wind turbine frequency amplitude in the wind turbine imbalance trend test array meets the suspicious condition for an abnormal wind turbine imbalance trend includes:

[0023] Determine the number of points in the wind turbine imbalance trend test array where the wind turbine frequency amplitude is greater than the benchmark value for judging abnormal wind turbine frequency amplitude trends;

[0024] Calculate the ratio of the number of points to the total number of points in the wind turbine frequency amplitude;

[0025] When the ratio exceeds the preset point percentage threshold, it is determined that the wind turbine frequency amplitude in the wind turbine imbalance change trend test array meets the abnormal suspicion condition of the wind turbine imbalance change trend.

[0026] Optionally, the process for determining the benchmark value for judging abnormal trends in the wind turbine frequency amplitude includes:

[0027] After the wind turbine is connected to the grid for the first time, the historical wind turbine frequency amplitude within a preset statistical period before the current time is obtained, and a statistical sample set of historical wind turbine frequency amplitude is formed.

[0028] Kernel density estimation is performed on the statistical sample set of historical wind turbine frequency amplitude to obtain the probability density function of wind turbine frequency amplitude;

[0029] The cumulative distribution function of the wind turbine rotation frequency amplitude probability density function is constructed by integral accumulation.

[0030] The target wind turbine frequency amplitude corresponding to the preset quantile position is found from the cumulative distribution function, and the target wind turbine frequency amplitude is used as the benchmark value for judging the abnormal trend of the wind turbine frequency amplitude change.

[0031] Optionally, the step of using a trend test method to diagnose long-term faults caused by abnormal wind turbine imbalance trends on the wind turbine imbalance change trend test array includes:

[0032] Based on the time series data of wind turbine frequency amplitude in the wind turbine imbalance change trend test array, calculate the wind turbine frequency amplitude statistic;

[0033] Calculate the variance of the wind turbine frequency amplitude statistic based on the size of the test array for the wind turbine imbalance change trend;

[0034] Calculate the standardized test statistic based on the wind turbine frequency amplitude statistic and the variance of the wind turbine frequency amplitude statistic;

[0035] A one-tailed hypothesis test is performed on the standardized test statistic. If the standardized test statistic is not less than the Z quantile corresponding to the preset percentile of the standard normal distribution, and the significance of the wind turbine imbalance trend is less than the preset significance level, it is determined that the risk unit has experienced an abnormally long-term fault in the wind turbine imbalance trend; otherwise, it is determined that the risk unit has not experienced an abnormally long-term fault in the wind turbine imbalance trend. The preset percentile is determined based on the preset significance level, and the Z quantile refers to the value corresponding to the cumulative probability equal to the preset percentile in the standard normal distribution, reflecting its deviation from the sample mean.

[0036] Optionally, the process of determining the target amplitude of the historical wind turbine rotation frequency includes:

[0037] After the wind turbine is connected to the grid for the first time, the historical wind turbine frequency amplitude within a preset statistical period before the current time is obtained, and a statistical sample set of historical wind turbine frequency amplitude is formed.

[0038] Calculate the average value of all historical wind turbine rotation frequency amplitudes in the statistical sample set of historical wind turbine rotation frequency amplitudes;

[0039] The average value is determined as the target amplitude of the historical wind turbine rotation frequency.

[0040] Optionally, the step of performing short-term fault diagnosis of abnormal wind turbine imbalance trend based on the changing trend of the cumulative deviation curve of wind turbine frequency amplitude includes:

[0041] Each cumulative deviation data point in the cumulative deviation curve of the wind turbine frequency amplitude is compared with the short-term trend abnormality judgment threshold of the wind turbine imbalance in chronological order.

[0042] If a preset number of cumulative deviation data points exceed the short-term trend abnormality judgment threshold for wind turbine imbalance, it is determined that the risk unit has experienced a short-term fault with abnormal wind turbine imbalance trend.

[0043] A wind turbine rotor imbalance fault diagnosis device includes:

[0044] The array acquisition unit is used to acquire the wind turbine frequency amplitude within a preset period when the wind turbine is in grid-connected power generation state, and to put each wind turbine frequency amplitude into the wind turbine imbalance change trend test array in chronological order;

[0045] The judgment unit is used to determine whether the preset period is greater than the long period threshold of the wind turbine imbalance change trend or less than the short period threshold of the wind turbine imbalance change trend.

[0046] The long-term fault diagnosis unit is used to perform long-term fault diagnosis of wind turbine imbalance trend abnormality on the wind turbine imbalance trend test array if the preset period is greater than the long-term threshold of the wind turbine imbalance change trend, and the wind turbine frequency amplitude in the wind turbine imbalance change trend test array meets the suspected condition of wind turbine imbalance change trend abnormality.

[0047] A short-term fault diagnosis unit is used to, if the preset period is less than the short-term threshold of the wind turbine imbalance change trend, sequentially calculate the cumulative deviation of each wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude according to the time sequence of each wind turbine frequency amplitude in the wind turbine imbalance change trend test array, and plot the cumulative deviation curve of the wind turbine frequency amplitude. Based on the changing trend of the cumulative deviation curve of the wind turbine frequency amplitude, a short-term fault diagnosis of the abnormal wind turbine imbalance change trend is performed. Each cumulative deviation is the sum of the deviation of the current time-series wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude and the cumulative deviation of the previous time-series wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude.

[0048] A computer storage medium storing at least one instruction, which, when executed by a processor, implements any method for diagnosing wind turbine rotor imbalance faults.

[0049] An electronic device, comprising: a memory and a processor;

[0050] The memory is used to store at least one instruction;

[0051] The processor is used to execute at least one instruction to implement any wind turbine rotor imbalance fault diagnosis method.

[0052] As can be seen from the above technical solution, the present invention discloses a method and related device for diagnosing wind turbine rotor imbalance faults. When the wind turbine is in grid-connected power generation, the rotor frequency amplitude within a preset period is obtained, and each rotor frequency amplitude is sequentially placed into a rotor imbalance trend test array according to the time sequence. When the preset period is greater than the long-term threshold of the rotor imbalance trend, and the rotor frequency amplitude in the rotor imbalance trend test array meets the suspected abnormality condition of the rotor imbalance trend, the trend test method is used to diagnose the long-term abnormality fault of the rotor imbalance trend in the rotor imbalance trend test array. When the preset period is less than the short-term threshold of the rotor imbalance trend, according to the time sequence of each rotor frequency amplitude in the rotor imbalance trend test array, the cumulative deviation of each rotor frequency amplitude relative to the historical rotor frequency target amplitude is calculated sequentially, and a cumulative deviation curve of rotor frequency amplitude is plotted. Based on the changing trend of the cumulative deviation curve of rotor frequency amplitude, a short-term abnormality fault of the rotor imbalance trend is diagnosed. This invention constructs a test array for wind turbine imbalance trends, considering two abnormal evolution modes of wind turbine imbalance (long-term slow cumulative change and short-term rapid change). It employs a dual-path parallel fusion strategy for pattern analysis, enabling long-term and short-term fault diagnosis of abnormal wind turbine imbalance trends. This strategy can capture both long-term, trend-enhancing features and remain sensitive to sudden, abrupt anomalies, effectively avoiding delayed or missed early fault reporting and significantly improving the early detection capability of wind turbine imbalance faults. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the published drawings without creative effort.

[0054] Figure 1 This is a flowchart of a wind turbine rotor imbalance fault diagnosis method disclosed in an embodiment of the present invention;

[0055] Figure 2 This is a schematic diagram illustrating an example of determining an abnormally long period of wind turbine imbalance trend according to an embodiment of the present invention.

[0056] Figure 3 This is a schematic diagram illustrating an example of calculating the benchmark value for judging the abnormal trend of wind turbine frequency amplitude variation and the target amplitude of historical wind turbine frequency, as disclosed in an embodiment of the present invention.

[0057] Figure 4 This is a schematic diagram illustrating an example of short-term abnormal determination of wind turbine imbalance trend disclosed in an embodiment of the present invention;

[0058] Figure 5 This is a schematic diagram of the structure of a wind turbine rotor imbalance fault diagnosis device disclosed in an embodiment of the present invention;

[0059] Figure 6 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention. Detailed Implementation

[0060] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] Existing wind turbine imbalance monitoring methods generally employ a static threshold strategy, triggering an alarm only when the turbine's rotational frequency amplitude exceeds a set threshold. This method only responds when the imbalance has progressed to the middle or later stages, with significantly increased vibration, often missing the optimal maintenance window. This leads to further deterioration of blade damage, increasing maintenance costs and downtime risks. The fundamental reason is that wind turbine operating conditions are complex, and minor changes caused by early imbalances are easily masked by wind speed fluctuations, pitch control, and other factors, rendering the static threshold strategy ineffective in identifying trend changes.

[0062] This invention, based on trend analysis, discloses a method for diagnosing wind turbine rotor imbalance faults. By constructing a test array for rotor imbalance change trends and considering two abnormal evolution modes of rotor imbalance (long-term slow cumulative change and short-term rapid change), a dual-path parallel fusion strategy is employed for pattern analysis, enabling both long-term and short-term fault diagnosis of abnormal rotor imbalance trends. This strategy can capture both long-term trend enhancement features and remain sensitive to sudden anomalies, effectively avoiding delayed or missed early fault reporting and significantly improving the early detection capability of wind turbine rotor imbalance faults.

[0063] See Figure 1 The present invention discloses a flowchart of a method for diagnosing wind turbine rotor imbalance faults, which includes:

[0064] Step S101: When the wind turbine is in grid-connected power generation state, obtain the wind turbine frequency amplitude within a preset period, and put each wind turbine frequency amplitude into the wind turbine imbalance change trend test array in sequence according to the time sequence.

[0065] When the wind turbine's operating status characteristics under any sliding window within a preset period meet the following judgment conditions, the wind turbine's rotational frequency amplitude corresponding to the sliding window is obtained. The wind turbine's operating status characteristics include: the standard deviation of the wind turbine's rotational speed, the wind turbine's rotational frequency, and the turbulence intensity.

[0066] The judgment criteria include:

[0067] (1) The standard deviation of the wind turbine speed is less than the threshold for judging the stability of the wind turbine speed.

[0068] The threshold value for judging the stability of the wind turbine speed is determined according to actual needs, such as setting it to 0.4 revolutions per minute.

[0069] (2) The absolute value of the difference between the wind turbine frequency and the first-order frequency of the tower is greater than the frequency difference threshold.

[0070] The frequency difference threshold is determined based on the frequency deviation adjustment coefficient. For example, the frequency difference threshold = tower first-order frequency × frequency deviation adjustment coefficient. The value of the frequency deviation adjustment coefficient is determined according to actual needs, for example, the frequency deviation adjustment coefficient is 10%.

[0071] (3) The turbulence intensity does not exceed the turbulence intensity threshold.

[0072] The turbulence intensity threshold can be the Class A turbulence intensity under the average wind speed over a preset time period in the IEC (International Electrotechnical Commission) standard. The Class A turbulence intensity is also the turbulence intensity in the IEC turbulence intensity curve.

[0073] In practical applications, the operating status characteristics of wind turbines can be determined using a sliding window algorithm based on their actual operating status parameters. These parameters are provided in real-time by the wind turbine's main control system and include at least: rotor speed, wind speed, and nacelle vibration signals.

[0074] The wind turbine rotation speed includes all wind turbine rotation speeds collected within a preset time period prior to the current moment.

[0075] Similarly, wind speed includes all wind speeds collected within a preset time period prior to the current moment.

[0076] The cabin vibration signal includes the cabin longitudinal vibration signal and the cabin lateral vibration signal.

[0077] In this embodiment, the value of the preset time period is determined according to actual needs, such as 10 minutes.

[0078] It should be noted that the preset period in this embodiment includes multiple sliding windows, and each sliding window is also the preset time period in this embodiment.

[0079] Step S102: Determine whether the preset period is greater than the long-term threshold of the wind turbine imbalance trend or less than the short-term threshold of the wind turbine imbalance trend. If the preset period is greater than the long-term threshold of the wind turbine imbalance trend, proceed to step S103; if the preset period is less than the short-term threshold of the wind turbine imbalance trend, proceed to step S104.

[0080] Through research, the inventors discovered that damage to wind turbine blades, such as tip damage, internal bulges, and trailing edge cracks, typically takes days, weeks, or even longer to accumulate from its initial stage to cause significant rotor imbalance. However, under certain special circumstances, once the cracks reach a critical size or the adhesive layer suddenly fails, the vibration level increases sharply and quickly triggers severe rotor imbalance. Therefore, two abnormal patterns of rotor imbalance trends exist: short-term rapid changes and long-term slow changes.

[0081] Based on this, the present invention sets long-period thresholds and short-period thresholds for wind turbine imbalance trends. When the preset period is greater than the long-period threshold, a long-term fault diagnosis of the wind turbine imbalance trend is performed; when the preset period is less than the short-period threshold, a short-term fault diagnosis of the wind turbine imbalance trend is performed. The present invention considers both abnormal modes simultaneously through a dual-path parallel fusion approach, ensuring early warning and protection in scenarios of rapid deterioration of wind turbine imbalance.

[0082] The values ​​of the long-term threshold and the short-term threshold of the wind turbine imbalance trend are determined according to actual needs. For example, the long-term threshold of the wind turbine imbalance trend is 30 days, and the short-term threshold of the wind turbine imbalance trend is 1 day.

[0083] Step S103: If the wind turbine frequency amplitude in the wind turbine imbalance change trend test array meets the suspected condition of wind turbine imbalance change trend abnormality, the trend test method is used to perform long-term fault diagnosis of wind turbine imbalance change trend abnormality on the wind turbine imbalance change trend test array.

[0084] This application for fault diagnosis of abnormal long-term wind turbine imbalance trends mainly includes two steps:

[0085] Step 1: Check whether the wind turbine frequency amplitude in the wind turbine imbalance trend test array meets the suspicious conditions for abnormal wind turbine imbalance trend.

[0086] The second step will only proceed if the wind turbine frequency amplitude in the wind turbine imbalance trend test array meets the suspicious condition of wind turbine imbalance trend abnormality. Otherwise, the observation status will be maintained during the judgment period when the current wind turbine imbalance trend is abnormally long.

[0087] Step 2: Fault diagnosis for abnormally long-term wind turbine imbalance trend. Specifically, the trend test method is used to diagnose the fault for abnormally long-term wind turbine imbalance trend by analyzing the wind turbine imbalance trend test array.

[0088] In practical applications, trend testing methods can include the Mann-Kendall trend test, the Spearman rank correlation test, and the linear fit trend test.

[0089] The Mann-Kendall trend test is a climate diagnostic and forecasting technique. It can be used to determine whether there are abrupt changes in a sequence, and if so, the timing of the abrupt change can be determined.

[0090] This application determines that the wind turbine frequency amplitude in the wind turbine imbalance trend test array meets the suspected condition of abnormal wind turbine imbalance trend, and that the wind turbine imbalance trend is abnormally long-term fault when determining that the wind turbine imbalance trend is abnormally long-term fault.

[0091] Step S104: According to the time sequence of each wind turbine frequency amplitude in the wind turbine imbalance change trend test array, calculate the cumulative deviation of each wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude in turn, and draw the wind turbine frequency amplitude cumulative deviation curve. Based on the change trend of the wind turbine frequency amplitude cumulative deviation curve, perform short-term fault diagnosis of abnormal wind turbine imbalance change trend.

[0092] Each of the cumulative deviations is the sum of the deviation of the current timing wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude and the cumulative deviation of the previous timing wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude.

[0093] The specific process of plotting the cumulative deviation curve of the wind turbine frequency amplitude in this embodiment is as follows:

[0094] The time series data of the wind turbine frequency amplitude in the array for testing the trend of wind turbine imbalance are as follows: , , ..., Let m be the size of the array used to check the wind turbine imbalance trend. Then, perform the following steps:

[0095] (1);

[0096] (2);

[0097] In the formula, This represents the initial cumulative deviation of the wind turbine frequency amplitude from the historical target wind turbine frequency amplitude, and is generally 0.

[0098] This represents the i-th wind turbine frequency amplitude in the short-term trend test array for wind turbine imbalance, where i ranges from 1 to m.

[0099] This indicates the target amplitude of the historical wind turbine rotation frequency.

[0100] This represents the cumulative deviation of the i-th wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude, where i ranges from 1 to m.

[0101] This represents the cumulative deviation of the (i-1)th wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude, where i ranges from 1 to m.

[0102] Calculated Then, these accumulated deviations are connected in time sequence to obtain the cumulative deviation curve of the wind turbine frequency amplitude within the short-term judgment period of abnormal wind turbine imbalance trend. The short-term fault diagnosis of abnormal wind turbine imbalance trend can be performed based on the changing trend of the cumulative deviation curve of wind turbine frequency amplitude.

[0103] Among them, when the preset period is less than the short-term period threshold of the wind turbine imbalance change trend, the wind turbine imbalance change trend test array can be defined as: the wind turbine imbalance short-term trend test array.

[0104] In summary, this invention discloses a method for diagnosing wind turbine rotor imbalance faults. When the wind turbine is in grid-connected power generation mode, the rotor frequency amplitude within a preset period is obtained, and each rotor frequency amplitude is sequentially placed into a rotor imbalance trend verification array according to time sequence. When the preset period is greater than the long-term threshold for rotor imbalance trend, and the rotor frequency amplitude in the rotor imbalance trend verification array meets the suspected abnormality condition for rotor imbalance trend, a trend verification method is used to diagnose long-term abnormality faults in the rotor imbalance trend verification array. When the preset period is less than the short-term threshold for rotor imbalance trend, according to the time sequence of each rotor frequency amplitude in the rotor imbalance trend verification array, the cumulative deviation of each rotor frequency amplitude relative to the historical rotor frequency target amplitude is calculated sequentially, and a cumulative deviation curve of rotor frequency amplitude is plotted. Based on the changing trend of the cumulative deviation curve of rotor frequency amplitude, a short-term abnormality fault diagnosis of rotor imbalance trend is performed. This invention constructs a test array for wind turbine imbalance trends, considering two abnormal evolution modes of wind turbine imbalance (long-term slow cumulative change and short-term rapid change). It employs a dual-path parallel fusion strategy for pattern analysis, enabling long-term and short-term fault diagnosis of abnormal wind turbine imbalance trends. This strategy can capture both long-term, trend-enhancing features and remain sensitive to sudden, abrupt anomalies, effectively avoiding delayed or missed early fault reporting and significantly improving the early detection capability of wind turbine imbalance faults.

[0105] It should be noted that this invention requires two types of input signals when diagnosing wind turbine rotor imbalance faults:

[0106] (1) Main control signals: These include wind speed, rotor speed, nacelle vibration signals (front and rear and left and right directions) and other actual operating status parameters of the wind turbine. These parameters are provided in real time by the wind turbine main control system.

[0107] (2) Algorithm signal: The first-order frequency of the tower is provided by the wind turbine control strategy module running in the PLC (Programmable Logic Controller).

[0108] The first-order frequency of the tower is its natural frequency. The first-order frequency of the tower for different aircraft models can be obtained during the design phase through BLADE (Blade Load and Dynamic Environment) simulation. The frequency range of the first-order frequency of the tower is typically between 0.1 and 0.5 Hz.

[0109] If the algorithm is deployed in the wind turbine edge computing terminal or the field-level control system, all input data is directly transmitted from the main controller to the edge computing terminal or the field-level control system.

[0110] In one embodiment, a sliding window algorithm is used to determine the operating state characteristics of the wind turbine based on its actual operating state parameters. The process of determining the operating state characteristics of the wind turbine under any sliding window includes:

[0111] (1) Determine the standard deviation and average value of the wind turbine rotation speed within a preset time period based on the wind turbine rotation speed of the wind turbine.

[0112] The process for determining the average wind turbine speed is as follows: add up all the wind turbine speed values ​​to get a sum, and then divide the sum by the total number of wind turbine speeds to obtain the average wind turbine speed.

[0113] The standard deviation of wind turbine speed reflects the degree to which the wind turbine speed deviates from the average wind turbine speed; the larger the value, the more severe the speed fluctuation.

[0114] The formula for calculating the standard deviation of wind turbine speed is as follows:

[0115] (3);

[0116] In the formula, The standard deviation of the wind turbine speed. The total number of wind turbine rotation speeds. Let i be the rotational speed of the i-th wind turbine. This represents the average rotational speed of the wind turbine.

[0117] (2) The wind turbine rotation frequency is calculated based on the average wind turbine rotation speed.

[0118] Wind turbine rotation frequency refers to one frequency (unit: Hz) of the wind turbine rotation speed.

[0119] In this embodiment, the calculated wind turbine rotation frequency is equal to the average wind turbine rotation speed divided by 60.

[0120] (3) Find a wind turbine frequency identification frequency range within the preset range of the wind turbine frequency calculation value, and find the maximum amplitude value in the range corresponding to the wind turbine frequency identification frequency range in the nacelle vibration signal spectrum as the finally identified wind turbine frequency amplitude value, and take the frequency value corresponding to the maximum amplitude value in the nacelle vibration signal spectrum as the finally identified wind turbine frequency, wherein the nacelle vibration signal spectrum is obtained by performing FFT (Fast Fourier Transform) on the nacelle vibration signal.

[0121] The core principle of FFT is to decompose the Discrete Fourier Transform into smaller subproblems using a divide-and-conquer strategy, and to reduce redundant computations by utilizing the symmetry and periodicity of the twitch factor, thereby significantly reducing time complexity.

[0122] (4) Determine the turbulence intensity within the preset time period based on the wind speed of the wind turbine.

[0123] Referring to the calculation process of the average wind turbine rotation speed and the standard deviation of wind turbine rotation speed, the average wind speed and the standard deviation of wind speed within a preset time period are determined based on wind speed.

[0124] Turbulence intensity = standard deviation of wind speed ÷ average wind speed.

[0125] As can be seen from step S103, the fault diagnosis of abnormal long-term wind turbine imbalance trend in this application mainly includes two steps:

[0126] Step 1: Detect whether the wind turbine frequency amplitude in the wind turbine imbalance trend test array meets the suspicious conditions for abnormal wind turbine imbalance trend. The specific judgment process is as follows:

[0127] Determine the number of points in the wind turbine imbalance trend test array where the wind turbine frequency amplitude is greater than the benchmark value for judging abnormal wind turbine frequency amplitude trends;

[0128] Calculate the ratio of the number of points to the total number of points in the wind turbine frequency amplitude;

[0129] When the ratio exceeds the preset point percentage threshold, it is determined that the wind turbine frequency amplitude in the wind turbine imbalance change trend test array meets the abnormal suspicion condition of the wind turbine imbalance change trend.

[0130] The value of the preset percentage threshold is determined according to actual needs, for example, 30%.

[0131] It should be noted that this application will only proceed to the second step if the wind turbine frequency amplitude in the wind turbine imbalance trend test array meets the suspicious condition of wind turbine imbalance trend abnormality. Otherwise, the observation state will be maintained during the judgment period when the current wind turbine imbalance trend is abnormally long.

[0132] Step 2: Use the trend test method to diagnose long-term faults caused by abnormal wind turbine imbalance trend in the wind turbine imbalance test array.

[0133] Specifically, based on the time series data of wind turbine frequency amplitude in the wind turbine imbalance change trend test array, the wind turbine frequency amplitude statistic is calculated;

[0134] Calculate the variance of the wind turbine frequency amplitude statistic based on the size of the test array for the wind turbine imbalance change trend;

[0135] Calculate the standardized test statistic based on the wind turbine frequency amplitude statistic and the variance of the wind turbine frequency amplitude statistic;

[0136] A one-tailed hypothesis test is performed on the standardized test statistic. If the standardized test statistic is not less than the Z quantile corresponding to the preset percentile of the standard normal distribution, and the significance of the wind turbine imbalance trend is less than the preset significance level, it is determined that the risk unit has experienced an abnormally long-term fault in the wind turbine imbalance trend; otherwise, it is determined that the risk unit has not experienced an abnormally long-term fault in the wind turbine imbalance trend. The preset percentile is determined based on the preset significance level, and the Z quantile refers to the value corresponding to the cumulative probability equal to the preset percentile in the standard normal distribution, reflecting its deviation from the sample mean.

[0137] Taking the Mann-Kendall trend test method for diagnosing long-term faults with abnormal wind turbine imbalance trends as an example, the specific diagnostic process is as follows:

[0138] The time series data of the wind turbine frequency amplitude in the wind turbine imbalance trend test array are set as follows: Amp_1P1, Amp_1P2, ..., Amp_1P n Let n be the size of the array used to check the wind turbine imbalance trend. Then, perform the following steps:

[0139] A1. Calculate the statistical quantity S of the wind turbine rotational frequency amplitude;

[0140] (4);

[0141] The symbolic function is defined as follows:

[0142] (5);

[0143] A2. Calculate the variance Var(S) of the wind turbine rotation frequency amplitude statistic S;

[0144] (6);

[0145] A3. Calculate the standardized test statistic Z. MK ;

[0146] (7);

[0147] It should be noted that this application converts the wind turbine frequency amplitude statistic S into a standardized test statistic Z. MK This makes it possible for large sample data Z MK It can approximately satisfy the standard normal distribution.

[0148] A4. Determine the significance of the trend (one-tailed hypothesis test, calculate the p-value);

[0149] Null hypothesis H a The current trend of wind turbine imbalance changes is abnormally long, and the degree of wind turbine imbalance increases significantly within the judgment period.

[0150] Let the significance level be α (usually α = 0.05), and calculate the significance p-value as follows:

[0151] (8);

[0152] In the formula, the function Φ is the cumulative distribution function of the standard normal distribution. Z represents the standardized test statistic. MK The absolute value of.

[0153] If Z MK ≥Z 1-α If p < 0.05, then the null hypothesis H is accepted. a Otherwise, there would be no increasing trend in the degree of wind turbine imbalance. Where Z... 1-α This represents the Z quantile corresponding to the 100th (1-α)th percentile of the standard normal distribution.

[0154] In summary, the present invention employs a cascaded fusion diagnostic strategy that combines the outlier percentage results with the Mann-Kendall test results. This strategy considers both the "instantaneous exceedance of the wind turbine frequency amplitude change trend anomaly judgment benchmark value" and the "significance of trend deviation," forming a comprehensive algorithm that can quickly detect abnormal fluctuations and rigorously judge trend growth. This greatly improves the accuracy and robustness of diagnosing abnormal wind turbine imbalance change trends.

[0155] See Figure 2 This invention discloses a schematic diagram of an example of determining an abnormally long-term trend of wind turbine imbalance. The horizontal axis represents the data point number, and the vertical axis represents the wind turbine frequency amplitude. Taking a faulty wind turbine as an example, firstly, within the determination period of an abnormally long-term trend of wind turbine imbalance, a long-term trend test array containing 491 wind turbine frequency amplitudes is obtained through continuous sliding windowing; then, an abnormally long-term trend diagnosis of wind turbine imbalance is performed. This includes two sub-steps. The first step is "suspicion of abnormal wind turbine imbalance trend," where the percentage of points in the long-term trend test array whose wind turbine frequency amplitude is greater than the benchmark value for determining abnormal wind turbine frequency amplitude trend is calculated to be 35.64%, exceeding the preset percentage threshold (30%). The second step is "determining the trend anomaly of wind turbine imbalance." Using the Mann-Kendall trend test method, the wind turbine frequency amplitude statistic S = 56400, the variance Var(S) of the wind turbine frequency amplitude statistic S = 13192351.67, and the standardized statistic Z = 15.528. At a significance level of α = 0.05, Z is much larger than Z0.05. 1-α Since p < 0.05, the fault is determined to have occurred within the current period when the wind turbine imbalance trend is abnormally long.

[0156] Through research, the inventors discovered that the distribution of wind turbine frequency amplitude varies among different wind turbine units. In order to improve the accuracy and robustness of the diagnosis of abnormal wind turbine imbalance trends, a "one-machine-one-policy" strategy is adopted for each wind turbine unit when calculating the benchmark value for judging abnormal wind turbine frequency amplitude trends and the historical wind turbine frequency target amplitude.

[0157] (a) The process of determining the benchmark value for judging abnormal trends in wind turbine frequency amplitude includes:

[0158] B1. After the wind turbine is initially connected to the grid for power generation, obtain the historical wind turbine frequency amplitude within a preset statistical period prior to the current time, and form a statistical sample set of historical wind turbine frequency amplitude, according to the following rules:

[0159] For continuous sliding windows, the following judgments should be made:

[0160] (1) The standard deviation of the wind turbine speed is less than the threshold for judging the stability of the wind turbine speed.

[0161] The threshold value for judging the stability of the wind turbine speed is determined according to actual needs, such as setting it to 0.4 revolutions per minute.

[0162] (2) The absolute value of the difference between the wind turbine frequency and the first-order frequency of the tower is greater than the frequency difference threshold.

[0163] The frequency difference threshold is determined based on the frequency deviation adjustment coefficient. For example, the frequency difference threshold = tower first-order frequency × frequency deviation adjustment coefficient. The value of the frequency deviation adjustment coefficient is determined according to actual needs, for example, the frequency deviation adjustment coefficient is 10%.

[0164] (3) The turbulence intensity does not exceed the turbulence intensity threshold.

[0165] The turbulence intensity threshold can be the Class A turbulence intensity under the average wind speed over a preset time period in the IEC (International Electrotechnical Commission) standard. The Class A turbulence intensity is also the turbulence intensity in the IEC turbulence intensity curve.

[0166] If all the above conditions are met in the current sliding window, the wind turbine frequency amplitude of the current sliding window is added to the historical wind turbine frequency amplitude statistical sample set, and then the above judgment is continued in the next sliding window.

[0167] B2. Perform kernel density estimation on the statistical sample set of historical wind turbine frequency amplitude to obtain the probability density function of wind turbine frequency amplitude.

[0168] The core idea of ​​kernel density estimation (KDE) is to obtain an overall probability density estimate by placing a "kernel function" at each data point and superimposing all kernel functions.

[0169] The core idea of ​​the probability density function (PDF) is to describe the "probability" of a continuous random variable taking a value around a certain value through "density" rather than direct probability.

[0170] B3. Construct a cumulative distribution function for the probability density function of the wind turbine frequency amplitude by integral accumulation.

[0171] The cumulative distribution function (CDF) is a key tool in probability theory used to describe the probability distribution of random variables, representing the cumulative probability that a random variable takes a value less than or equal to a certain specific value.

[0172] The core idea of ​​the cumulative distribution function is to describe the sum of probabilities of a random variable within a certain range of values ​​by using cumulative probability.

[0173] B4. Find the target wind turbine frequency amplitude corresponding to the preset quantile position from the cumulative distribution function, and use the target wind turbine frequency amplitude as the benchmark value for judging the abnormal trend of the wind turbine frequency amplitude change.

[0174] The value of the preset quantile position is determined according to actual needs, for example, the 95th quantile position.

[0175] B5. Calculate the average value of all historical wind turbine rotation frequency amplitudes in the historical wind turbine rotation frequency amplitude statistical sample set, and determine the average value as the target amplitude of historical wind turbine rotation frequency.

[0176] See Figure 3 This invention discloses an example of calculating the benchmark value for judging the abnormal trend of wind turbine frequency amplitude variation and the target amplitude of historical wind turbine frequency variation. Taking a faulty wind turbine as an example, within a preset statistical period, a statistical sample set of historical wind turbine frequency amplitude containing 6015 wind turbine frequency amplitudes is obtained through continuous sliding windowing, and a probability distribution histogram is plotted. The probability density function of the wind turbine frequency amplitude is obtained through kernel density estimation. Then, the cumulative distribution function of the wind turbine frequency amplitude is constructed by accumulation. Finally, the 95th percentile position in the cumulative distribution function is used as the benchmark value for judging the abnormal trend of wind turbine frequency amplitude variation for the faulty turbine. In this embodiment, the benchmark value for judging the abnormal trend of wind turbine frequency amplitude variation is 0.0073g (i.e., Figure 3The vertical dashed line 11 corresponds to 0.0073g), and the average value of the historical wind turbine frequency amplitude statistical sample set is used as the historical wind turbine frequency target amplitude of the faulty unit. In this embodiment, the historical wind turbine frequency target amplitude is 0.0027g (i.e., Figure 3 The vertical dashed line 12 corresponds to 0.0027g.

[0177] In one embodiment, the process of diagnosing short-term faults caused by abnormal wind turbine imbalance trends based on the changing trend of the cumulative deviation curve of wind turbine frequency amplitude includes:

[0178] Each cumulative deviation data point in the cumulative deviation curve of wind turbine frequency amplitude is compared with the threshold for judging short-term trend anomalies of wind turbine imbalance in chronological order.

[0179] If a preset number of cumulative deviation data points exceed the threshold for judging short-term abnormal trends in wind turbine imbalance, it is determined that the risky unit has experienced a short-term fault with abnormal wind turbine imbalance trend.

[0180] The threshold value for judging the short-term trend anomaly of wind turbine imbalance is determined according to actual needs, for example, 0.05g, where g is the unit of acceleration.

[0181] The value of the consecutive preset quantity depends on the actual needs. For example, the value of the consecutive preset quantity is 5. This invention does not limit this value.

[0182] See Figure 4 This invention discloses an example of a short-term determination of abnormal wind turbine imbalance trends. Taking a faulty wind turbine as an example, firstly, within the short-term determination period of abnormal wind turbine imbalance trends, a test array of wind turbine imbalance trends containing 43 wind turbine frequency amplitudes is obtained through continuous sliding windowing; then, a short-term diagnosis of abnormal wind turbine imbalance trends is performed, and the results are calculated. Then, the cumulative deviation curve of the wind turbine frequency amplitude was plotted (blue curve in the figure); finally, the magnitude of each cumulative deviation data point in the cumulative deviation curve of the wind turbine frequency amplitude was compared with the threshold for judging the short-term trend anomaly of the wind turbine imbalance. As shown in the figure, starting from number 19 (the position corresponding to the pink vertical dashed line in the figure, with a cumulative deviation value of 0.05225g), the cumulative deviation curve of the wind turbine frequency amplitude exceeded the threshold for judging the short-term trend anomaly of the wind turbine imbalance (0.05g) for multiple consecutive points. At number 23 (the position corresponding to the orange vertical dashed line in the figure), the short-term trend anomaly warning logic was triggered. Therefore, the short-term judgment of the wind turbine imbalance change trend anomaly was established.

[0183] Corresponding to the above method embodiments, the present invention also discloses a wind turbine rotor imbalance fault diagnosis device.

[0184] See Figure 5The present invention discloses a structural schematic diagram of a wind turbine rotor imbalance fault diagnosis device, which may include:

[0185] The array acquisition unit 201 is used to acquire the wind turbine frequency amplitude within a preset period when the wind turbine is in the grid-connected power generation state, and to put each wind turbine frequency amplitude into the wind turbine imbalance change trend test array in chronological order;

[0186] Judgment unit 202 is used to determine whether the preset period is greater than the long period threshold of the wind turbine imbalance change trend or less than the short period threshold of the wind turbine imbalance change trend.

[0187] The long-term fault diagnosis unit 203 is used to perform long-term fault diagnosis of wind turbine imbalance trend abnormality on the wind turbine imbalance trend test array if the preset period is greater than the long-term threshold of the wind turbine imbalance change trend, and the wind turbine frequency amplitude in the wind turbine imbalance change trend test array meets the suspected condition of wind turbine imbalance change trend abnormality.

[0188] The short-term fault diagnosis unit 204 is used to calculate the cumulative deviation of each wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude according to the time sequence of each wind turbine frequency amplitude in the wind turbine imbalance change trend test array if the preset period is less than the short-term threshold of the wind turbine imbalance change trend. The unit also plots the cumulative deviation curve of the wind turbine frequency amplitude and performs short-term fault diagnosis of the wind turbine imbalance change trend based on the changing trend of the cumulative deviation curve. Each cumulative deviation is the sum of the deviation of the current time sequence wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude and the cumulative deviation of the previous time sequence wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude.

[0189] In summary, this invention discloses a wind turbine rotor imbalance fault diagnosis device. When the wind turbine is in grid-connected power generation mode, it acquires the rotor frequency amplitude within a preset period and sequentially places each rotor frequency amplitude into a rotor imbalance trend verification array according to time sequence. When the preset period is greater than the long-term threshold of the rotor imbalance trend, and the rotor frequency amplitude in the rotor imbalance trend verification array meets the suspected abnormality condition of the rotor imbalance trend, a trend verification method is used to diagnose a long-term abnormality fault in the rotor imbalance trend verification array. When the preset period is less than the short-term threshold of the rotor imbalance trend, according to the time sequence of each rotor frequency amplitude in the rotor imbalance trend verification array, the cumulative deviation of each rotor frequency amplitude relative to the historical rotor frequency target amplitude is calculated sequentially, and a cumulative deviation curve of the rotor frequency amplitude is plotted. Based on the changing trend of the cumulative deviation curve of the rotor frequency amplitude, a short-term abnormality fault diagnosis of the rotor imbalance trend is performed. This invention constructs a test array for wind turbine imbalance trends, considering two abnormal evolution modes of wind turbine imbalance (long-term slow cumulative change and short-term rapid change). It employs a dual-path parallel fusion strategy for pattern analysis, enabling long-term and short-term fault diagnosis of abnormal wind turbine imbalance trends. This strategy can capture both long-term, trend-enhancing features and remain sensitive to sudden, abrupt anomalies, effectively avoiding delayed or missed early fault reporting and significantly improving the early detection capability of wind turbine imbalance faults.

[0190] In one embodiment, the array acquisition unit 201 can be specifically used for:

[0191] When the wind turbine operating state characteristics under any sliding window within the preset period meet the following judgment conditions, the wind turbine rotation frequency amplitude value corresponding to the sliding window is obtained, and the judgment conditions include:

[0192] The standard deviation of the wind turbine speed is less than the threshold for judging the stability of the wind turbine speed.

[0193] The absolute value of the difference between the wind turbine frequency and the tower's first-order frequency is greater than the frequency difference threshold, which is determined based on the frequency deviation adjustment coefficient.

[0194] The turbulence intensity did not exceed the turbulence intensity threshold.

[0195] The operating characteristics of the wind turbine include: the standard deviation of the wind turbine rotation speed, the wind turbine rotation frequency, and the turbulence intensity.

[0196] In one embodiment, the array acquisition unit 201 can be specifically used for:

[0197] Based on the wind turbine rotor speed of the wind turbine, determine the standard deviation and average value of the wind turbine rotor speed within a preset time period;

[0198] The wind turbine frequency is calculated based on the average wind turbine rotation speed.

[0199] A wind turbine frequency identification frequency range is found within a preset range of the calculated wind turbine frequency value. The maximum amplitude value is found in the range corresponding to the wind turbine frequency identification frequency range in the nacelle vibration signal spectrum as the final identified wind turbine frequency amplitude value. The frequency value corresponding to the maximum amplitude value in the nacelle vibration signal spectrum is taken as the final identified wind turbine frequency. The nacelle vibration signal spectrum is obtained by performing a fast Fourier transform on the nacelle vibration signal.

[0200] The turbulence intensity within the preset time period is determined based on the wind speed of the wind turbine.

[0201] In one embodiment, the long-term fault diagnosis unit 203 can be specifically used for:

[0202] Determine the number of points in the wind turbine imbalance trend test array where the wind turbine frequency amplitude is greater than the benchmark value for judging abnormal wind turbine frequency amplitude trends;

[0203] Calculate the ratio of the number of points to the total number of points in the wind turbine frequency amplitude;

[0204] When the ratio exceeds the preset point percentage threshold, it is determined that the wind turbine frequency amplitude in the wind turbine imbalance change trend test array meets the abnormal suspicion condition of the wind turbine imbalance change trend.

[0205] In one embodiment, the wind turbine rotor imbalance fault diagnosis device may further include:

[0206] The unit for determining the benchmark value for judging abnormal trends in wind turbine frequency amplitude variation is used for:

[0207] After the wind turbine is connected to the grid for the first time, the historical wind turbine frequency amplitude within a preset statistical period before the current time is obtained, and a statistical sample set of historical wind turbine frequency amplitude is formed.

[0208] Kernel density estimation is performed on the statistical sample set of historical wind turbine frequency amplitude to obtain the probability density function of wind turbine frequency amplitude;

[0209] The cumulative distribution function of the wind turbine rotation frequency amplitude probability density function is constructed by integral accumulation.

[0210] The target wind turbine frequency amplitude corresponding to the preset quantile position is found from the cumulative distribution function, and the target wind turbine frequency amplitude is used as the benchmark value for judging the abnormal trend of the wind turbine frequency amplitude change.

[0211] In one embodiment, the long-term fault diagnosis unit 203 can also be used for:

[0212] Based on the time series data of wind turbine frequency amplitude in the wind turbine imbalance change trend test array, calculate the wind turbine frequency amplitude statistic;

[0213] Calculate the variance of the wind turbine frequency amplitude statistic based on the size of the test array for the wind turbine imbalance change trend;

[0214] Calculate the standardized test statistic based on the wind turbine frequency amplitude statistic and the variance of the wind turbine frequency amplitude statistic;

[0215] A one-tailed hypothesis test is performed on the standardized test statistic. If the standardized test statistic is not less than the Z quantile corresponding to the preset percentile of the standard normal distribution, and the significance of the wind turbine imbalance trend is less than the preset significance level, it is determined that the risk unit has experienced an abnormally long-term fault in the wind turbine imbalance trend; otherwise, it is determined that the risk unit has not experienced an abnormally long-term fault in the wind turbine imbalance trend. The preset percentile is determined based on the preset significance level, and the Z quantile refers to the value corresponding to the cumulative probability equal to the preset percentile in the standard normal distribution, reflecting its deviation from the sample mean.

[0216] In one embodiment, the wind turbine rotor imbalance fault diagnosis device may further include:

[0217] The historical wind turbine frequency target amplitude determination unit is used for:

[0218] After the wind turbine is connected to the grid for the first time, the historical wind turbine frequency amplitude within a preset statistical period before the current time is obtained, and a statistical sample set of historical wind turbine frequency amplitude is formed.

[0219] Calculate the average value of all historical wind turbine rotation frequency amplitudes in the statistical sample set of historical wind turbine rotation frequency amplitudes;

[0220] The average value is determined as the target amplitude of the historical wind turbine rotation frequency.

[0221] In one embodiment, the short-time fault diagnosis unit 204 can be specifically used for:

[0222] Each cumulative deviation data point in the cumulative deviation curve of the wind turbine frequency amplitude is compared with the short-term trend abnormality judgment threshold of the wind turbine imbalance in chronological order.

[0223] If a preset number of cumulative deviation data points exceed the short-term trend abnormality judgment threshold for wind turbine imbalance, it is determined that the risk unit has experienced a short-term fault with abnormal wind turbine imbalance trend.

[0224] It should be noted that for the specific working principles of each component in the device embodiment, please refer to the corresponding section of the method embodiment, which will not be repeated here.

[0225] Corresponding to the above embodiments, the present invention also discloses a computer storage medium that stores at least one instruction, which, when executed by a processor, implements the steps shown in the embodiments of the wind turbine rotor imbalance fault diagnosis method.

[0226] Computer storage media can be tangible media that may contain or store programs for use by or in conjunction with an instruction execution system, apparatus, or device. Computer storage media can be machine-readable signal media or machine-readable storage media. Computer storage media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0227] Corresponding to the above embodiments, such as Figure 6 As shown, the present invention also provides a schematic diagram of the structure of an electronic device, which may include: a processor 1 and a memory 2;

[0228] The processor 1 and memory 2 communicate with each other via communication bus 3.

[0229] Processor 1, for executing at least one instruction;

[0230] Memory 2 is used to store at least one instruction;

[0231] Processor 1 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention.

[0232] Memory 2 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0233] In this embodiment, the processor executes at least one instruction to implement the steps shown in the wind turbine rotor imbalance fault diagnosis method.

[0234] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0235] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0236] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A wind turbine generator rotor imbalance fault diagnosis method, characterized in that, include: When the wind turbine is in grid-connected power generation state, the wind turbine frequency amplitude within a preset period is obtained, and each wind turbine frequency amplitude is sequentially placed into the wind turbine imbalance change trend test array according to the time sequence. It is determined whether the preset period is greater than the long-period threshold of the wind turbine imbalance change trend or less than the short-period threshold of the wind turbine imbalance change trend. If the preset period is greater than the long period threshold of the wind turbine imbalance change trend, and the wind turbine frequency amplitude in the wind turbine imbalance change trend test array meets the suspected abnormal wind turbine imbalance change trend condition, the trend test method is used to perform long-term fault diagnosis of the wind turbine imbalance change trend abnormality in the wind turbine imbalance change trend test array. If the preset period is less than the short-period threshold of the wind turbine imbalance change trend, the cumulative deviation of each wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude is calculated sequentially according to the time sequence of each wind turbine frequency amplitude in the wind turbine imbalance change trend test array, and the cumulative deviation curve of wind turbine frequency amplitude is plotted. The abnormal short-term fault diagnosis of wind turbine imbalance change trend is performed based on the changing trend of the cumulative deviation curve of wind turbine frequency amplitude. Each cumulative deviation is: the sum of the deviation of the current time sequence wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude and the cumulative deviation of the previous time sequence wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude. The step of using a trend test method to diagnose long-term faults caused by abnormal wind turbine imbalance trends in the wind turbine imbalance trend test array includes: Based on the time series data of wind turbine frequency amplitude in the wind turbine imbalance change trend test array, calculate the wind turbine frequency amplitude statistic; Calculate the variance of the wind turbine frequency amplitude statistic based on the size of the test array for the wind turbine imbalance change trend; Calculate the standardized test statistic based on the wind turbine frequency amplitude statistic and the variance of the wind turbine frequency amplitude statistic; A one-tailed hypothesis test is performed on the standardized test statistic. If the standardized test statistic is not less than the Z quantile corresponding to the preset percentile of the standard normal distribution, and the significance of the wind turbine imbalance trend is less than the preset significance level, it is determined that the wind turbine has experienced an abnormally long-term fault in the wind turbine imbalance trend; otherwise, it is determined that the wind turbine has not experienced an abnormally long-term fault in the wind turbine imbalance trend. The preset percentile is determined based on the preset significance level, and the Z quantile refers to the value corresponding to the cumulative probability equal to the preset percentile in the standard normal distribution, reflecting its deviation from the sample mean.

2. The wind turbine generator rotor imbalance fault diagnostic method according to claim 1, characterized by, The step of obtaining the wind turbine rotation frequency amplitude within a preset period includes: When the wind turbine operating state characteristics under any sliding window within the preset period meet the following judgment conditions, the wind turbine rotation frequency amplitude value corresponding to the sliding window is obtained, and the judgment conditions include: The standard deviation of the wind turbine speed is less than the threshold for judging the stability of the wind turbine speed. The absolute value of the difference between the wind turbine frequency and the tower's first-order frequency is greater than the frequency difference threshold, which is determined based on the frequency deviation adjustment coefficient. The turbulence intensity did not exceed the turbulence intensity threshold. The operating characteristics of the wind turbine include: the standard deviation of the wind turbine rotation speed, the wind turbine rotation frequency, and the turbulence intensity.

3. The wind turbine generator rotor imbalance fault diagnostic method according to claim 2, characterized by, The process of determining the operating state characteristics of the wind turbine under any sliding window includes: Based on the wind turbine rotor speed of the wind turbine, determine the standard deviation and average value of the wind turbine rotor speed within a preset time period; The wind turbine frequency is calculated based on the average wind turbine rotation speed. A wind turbine frequency identification frequency range is found within a preset range of the calculated wind turbine frequency value. The maximum amplitude value is found in the range corresponding to the wind turbine frequency identification frequency range in the nacelle vibration signal spectrum as the final identified wind turbine frequency amplitude value. The frequency value corresponding to the maximum amplitude value in the nacelle vibration signal spectrum is taken as the final identified wind turbine frequency. The nacelle vibration signal spectrum is obtained by performing a fast Fourier transform on the nacelle vibration signal. The turbulence intensity within the preset time period is determined based on the wind speed of the wind turbine.

4. The wind turbine imbalance fault diagnosis method according to any one of claims 1-3, characterized in that, The process for determining whether the wind turbine frequency amplitude in the wind turbine imbalance trend test array meets the suspicious condition for wind turbine imbalance trend includes: Determine the number of points in the wind turbine imbalance trend test array where the wind turbine frequency amplitude is greater than the benchmark value for judging abnormal wind turbine frequency amplitude trends; Calculate the ratio of the number of points to the total number of points in the wind turbine frequency amplitude; When the ratio exceeds the preset point percentage threshold, it is determined that the wind turbine frequency amplitude in the wind turbine imbalance change trend test array meets the abnormal suspicion condition of the wind turbine imbalance change trend.

5. The wind turbine generator rotor imbalance fault diagnostic method according to claim 4, characterized by, The process for determining the benchmark value for judging abnormal trends in wind turbine rotation frequency amplitude includes: After the wind turbine is connected to the grid for the first time, the historical wind turbine frequency amplitude within a preset statistical period before the current time is obtained, and a statistical sample set of historical wind turbine frequency amplitude is formed. Kernel density estimation is performed on the statistical sample set of historical wind turbine frequency amplitude to obtain the probability density function of wind turbine frequency amplitude; The cumulative distribution function of the wind turbine rotation frequency amplitude probability density function is constructed by integral accumulation. The target wind turbine frequency amplitude corresponding to the preset quantile position is found from the cumulative distribution function, and the target wind turbine frequency amplitude is used as the benchmark value for judging the abnormal trend of the wind turbine frequency amplitude change.

6. The wind turbine generator rotor imbalance fault diagnostic method of claim 1, wherein, The process for determining the target amplitude of the historical wind turbine rotation frequency includes: After the wind turbine is connected to the grid for the first time, the historical wind turbine frequency amplitude within a preset statistical period before the current time is obtained, and a statistical sample set of historical wind turbine frequency amplitude is formed. Calculate the average value of all historical wind turbine rotation frequency amplitudes in the statistical sample set of historical wind turbine rotation frequency amplitudes; The average value is determined as the target amplitude of the historical wind turbine rotation frequency.

7. The wind turbine generator rotor imbalance fault diagnostic method of claim 1, wherein, The method of diagnosing short-term faults caused by abnormal wind turbine imbalance trends based on the changing trend of the cumulative deviation curve of wind turbine frequency amplitude includes: Each cumulative deviation data point in the cumulative deviation curve of the wind turbine frequency amplitude is compared with the short-term trend abnormality judgment threshold of the wind turbine imbalance in chronological order. If a preset number of cumulative deviation data points exceed the short-term trend abnormality judgment threshold for wind turbine imbalance, it is determined that the wind turbine has experienced a short-term fault with abnormal wind turbine imbalance trend.

8. A wind turbine generator wind wheel unbalance fault diagnosis device, which adopts the wind turbine generator wind wheel unbalance fault diagnosis method of claim 1, characterized in that, include: The array acquisition unit is used to acquire the wind turbine frequency amplitude within a preset period when the wind turbine is in grid-connected power generation state, and to put each wind turbine frequency amplitude into the wind turbine imbalance change trend test array in chronological order; The judgment unit is used to determine whether the preset period is greater than the long period threshold of the wind turbine imbalance change trend or less than the short period threshold of the wind turbine imbalance change trend. The long-term fault diagnosis unit is used to perform long-term fault diagnosis of wind turbine imbalance trend abnormality on the wind turbine imbalance trend test array if the preset period is greater than the long-term threshold of the wind turbine imbalance change trend, and the wind turbine frequency amplitude in the wind turbine imbalance change trend test array meets the suspected condition of wind turbine imbalance change trend abnormality. A short-term fault diagnosis unit is used to, if the preset period is less than the short-term threshold of the wind turbine imbalance change trend, sequentially calculate the cumulative deviation of each wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude according to the time sequence of each wind turbine frequency amplitude in the wind turbine imbalance change trend test array, and plot the cumulative deviation curve of the wind turbine frequency amplitude. Based on the changing trend of the cumulative deviation curve of the wind turbine frequency amplitude, a short-term fault diagnosis of the abnormal wind turbine imbalance change trend is performed. Each cumulative deviation is the sum of the deviation of the current time-series wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude and the cumulative deviation of the previous time-series wind turbine frequency amplitude relative to the historical wind turbine frequency target amplitude.

9. A computer storage medium, characterized in that, The computer storage medium stores at least one instruction, which, when executed by the processor, implements the wind turbine rotor imbalance fault diagnosis method as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, The electronic device includes: a memory and a processor; The memory is used to store at least one instruction; The processor is used to execute at least one instruction to implement the wind turbine rotor imbalance fault diagnosis method as described in any one of claims 1 to 7.

Images