Methods and devices for early warning and diagnosis of yaw faults in wind turbine generators

Abstract

This disclosure relates to a method and apparatus for early warning and diagnosis of yaw faults in wind turbine generator sets. The method includes: acquiring operating data of the wind turbine generator set in a non-yaw state and operating data in a yaw state; determining a first statistical characteristic value of the operating data of the wind turbine generator set in a non-yaw state and a second statistical characteristic value of the operating data of the wind turbine generator set in a yaw state for each rotor speed range of the wind turbine generator set; and determining that a yaw fault has occurred in the wind turbine generator set or the cause of the yaw fault is determined in response to at least one of the first and second statistical characteristic values ​​satisfying a preset condition. By adopting this disclosure, yaw vibration status can be monitored under all operating conditions, and the cause of the fault and the corresponding operating condition can be accurately diagnosed after a yaw fault occurs, without the need for additional sensing equipment, which helps to improve unit stability, reduce operation and maintenance costs, and reduce power generation loss.

Description

Technical Field

[0001] This disclosure relates to the field of wind power generation technology, and more specifically, to a method and device for early warning and diagnosis of yaw faults in wind turbine generator sets. Background Technology

[0002] Most wind turbine yaw control systems employ active yaw to adjust the rotor's windward position in real time, maximizing wind energy capture and reducing load. Hydraulic yaw braking systems are commonly used. Frequent yaw and braking can lead to yaw vibration instability and yaw brake wear, resulting in over-acceleration faults and turbine shutdown. While wind turbines typically reset automatically after a period of time following an over-acceleration fault, if the underlying cause is not identified, the fault can recur. Frequent start-stop cycles can shorten the lifespan of components, increase maintenance difficulty and costs, and cause power generation losses. There are many causes of over-acceleration yaw faults, including yaw-coupled vibration, extreme wind conditions, tower shadow effect, tower-coupled vibration, pitch-coupled vibration, main control system-coupled vibration, and electrical system-coupled vibration causing resonance. Improper installation, looseness, or abnormal noise from acceleration sensors can also lead to frequent over-acceleration fault reports. Typically, high-frequency vibration data can be collected by installing high-frequency vibration sensors on key components, and fault features can be extracted using time-domain and frequency-domain methods to achieve unit vibration status monitoring and fault diagnosis. However, this approach suffers from susceptibility to noise and high cost. Furthermore, existing solutions for monitoring yaw brake system components primarily monitor the yaw brake pads, pad thickness, and wear condition to assess the system's operational status. These solutions require additional sensors, have limited functionality, and cannot comprehensively monitor yaw vibration anomalies or diagnose the causes of yaw acceleration exceeding limits. Additionally, machine learning-based solutions suffer from overfitting and poor interpretability. For example, in a wind turbine nacelle vibration fault diagnosis system and method based on Naive Bayes algorithms, the samples used must satisfy the conditional independence assumption. However, yaw-related data (wind speed, wind direction, yaw command, yaw brake pressure, nacelle acceleration, etc.) are highly coupled, leading to risks of overfitting and poor interpretability in the algorithm. In summary, there are many reasons for excessive yaw acceleration faults in aircraft, making it difficult to accurately predict and diagnose such faults. Furthermore, existing solutions suffer from problems such as susceptibility to noise, high cost, the need for additional sensors, and risks of overfitting and poor interpretability in the algorithms. Summary of the Invention

[0003] To address the aforementioned issues, this disclosure proposes a method and device for early warning and diagnosis of yaw faults in wind turbine generator sets, a computing system, and a computer-readable storage medium.

[0004] According to one aspect of this disclosure, a method for early warning and diagnosis of yaw faults in a wind turbine generator set is provided. The method includes: acquiring operating data of the wind turbine generator set in a non-yaw state and operating data in a yaw state; determining a first statistical characteristic value of the operating data of the wind turbine generator set in a non-yaw state and a second statistical characteristic value of the operating data of the wind turbine generator set in a yaw state for each rotor speed range of the wind turbine generator set; and determining that a yaw fault has occurred in the wind turbine generator set or the cause of the yaw fault has occurred in the wind turbine generator set in response to at least one of the first statistical characteristic value and the second statistical characteristic value satisfying a preset condition.

[0005] Optionally, the first statistical characteristic value includes the mean and variance of the effective value of the nacelle acceleration and the median of the yaw residual pressure when the wind turbine generator is in a non-yaw state, and the second statistical characteristic value includes the mean and variance of the effective value of the nacelle acceleration and the median of the yaw residual pressure when the wind turbine generator is in a yaw state.

[0006] Optionally, the first statistical feature value is the median yaw residual pressure of the wind turbine generator set in a non-yaw state, and the second statistical feature value is the median yaw residual pressure of the wind turbine generator set in a yaw state. The step of determining that the wind turbine generator set has a yaw fault or determining the cause of the yaw fault in response to at least one of the first and second statistical feature values ​​satisfying a preset condition includes: determining that the wind turbine generator set has an abnormal yaw residual pressure or determining that the cause of the yaw fault in the wind turbine generator set is an abnormal yaw residual pressure in response to at least one of the first and second statistical feature values ​​exceeding a preset range.

[0007] Optionally, the first statistical feature value is the average effective value of the nacelle acceleration of the wind turbine generator set in a non-yaw state, and the second statistical feature value is the average effective value of the nacelle acceleration of the wind turbine generator set in a yaw state. The step of determining that the wind turbine generator set has a yaw fault or determining the cause of the yaw fault in response to at least one of the first and second statistical feature values ​​satisfying a preset condition includes: determining that the wind turbine generator set has an acceleration sensor malfunction or determining that the cause of the yaw fault in the wind turbine generator set is an acceleration sensor malfunction in response to at least one of the first and second statistical feature values ​​being greater than a predetermined threshold.

[0008] Optionally, the first statistical feature value is the variance of the effective value of the nacelle acceleration of the wind turbine generator set in a non-yaw state, and the second statistical feature value is the variance of the effective value of the nacelle acceleration of the wind turbine generator set in a yaw state. The step of determining that the wind turbine generator set has a yaw fault or determining the cause of the yaw fault in response to at least one of the first and second statistical feature values ​​satisfying a preset condition includes: determining that the wind turbine generator set has yaw vibration abnormality or determining that the cause of the yaw fault in the wind turbine generator set is yaw vibration abnormality in response to the first statistical feature value being less than a first threshold and the second statistical feature value being greater than a second threshold.

[0009] Optionally, the first statistical feature value is the variance of the effective value of the nacelle acceleration when the wind turbine is in a non-yaw state, and the second statistical feature value is the variance of the effective value of the nacelle acceleration when the wind turbine is in a yaw state. The step of determining whether the wind turbine has a yaw fault or the cause of the yaw fault, in response to at least one of the first and second statistical feature values ​​satisfying a preset condition, includes: for the rotor speed range indicating that the wind turbine is in a stopped or started yaw-facing wind state, in response to the first statistical feature value being less than a first threshold and the second statistical feature value being greater than a third threshold, determining that the cause of the yaw fault is tower resonance or a yaw brake system malfunction when the wind turbine is stopped or started yaw-facing wind.

[0010] Optionally, the first statistical feature value is the variance of the effective value of the nacelle acceleration when the wind turbine is in a non-yaw state, and the second statistical feature value is the variance of the effective value of the nacelle acceleration when the wind turbine is in a yaw state. The step of determining whether the wind turbine has a yaw fault or the cause of the yaw fault, in response to at least one of the first and second statistical feature values ​​satisfying a preset condition, includes: for the rotor speed range indicating that the wind turbine is in a grid-connected power generation state, in response to the first statistical feature value being less than a first threshold and the second statistical feature value being greater than a third threshold, determining that the cause of the yaw fault is unstable yaw torque or abnormal yaw noise.

[0011] According to another aspect of this disclosure, a yaw fault early warning and diagnosis device for a wind turbine generator set is provided. The device includes: a data acquisition unit for acquiring operating data of the wind turbine generator set in a non-yaw state and operating data in a yaw state; a statistical feature value determination unit for determining a first statistical feature value of the operating data of the wind turbine generator set in a non-yaw state and a second statistical feature value of the operating data of the wind turbine generator set in a yaw state for each rotor speed range of the wind turbine generator set; and an early warning and diagnosis unit for determining that a yaw fault has occurred in the wind turbine generator set or determining the cause of the yaw fault in the wind turbine generator set in response to at least one of the first statistical feature value and the second statistical feature value satisfying a preset condition.

[0012] Optionally, the first statistical characteristic value includes the mean and variance of the effective value of the nacelle acceleration and the median of the yaw residual pressure when the wind turbine generator is in a non-yaw state, and the second statistical characteristic value includes the mean and variance of the effective value of the nacelle acceleration and the median of the yaw residual pressure when the wind turbine generator is in a yaw state.

[0013] Optionally, the first statistical feature value is the median yaw residual pressure of the wind turbine generator set in a non-yaw state, and the second statistical feature value is the median yaw residual pressure of the wind turbine generator set in a yaw state. The early warning and diagnosis unit determines that the wind turbine generator set has an abnormal yaw residual pressure or determines that the cause of the yaw failure of the wind turbine generator set is an abnormal yaw residual pressure when at least one of the first statistical feature value and the second statistical feature value exceeds a preset range.

[0014] Optionally, the first statistical feature value is the average effective value of the nacelle acceleration when the wind turbine generator is in a non-yaw state, and the second statistical feature value is the average effective value of the nacelle acceleration when the wind turbine generator is in a yaw state. The early warning and diagnosis unit determines that the wind turbine generator has an acceleration sensor malfunction or determines that the cause of the yaw fault of the wind turbine generator is an acceleration sensor malfunction when at least one of the first statistical feature value and the second statistical feature value is greater than a predetermined threshold.

[0015] Optionally, the first statistical feature value is the variance of the effective value of the nacelle acceleration of the wind turbine generator set in a non-yaw state, and the second statistical feature value is the variance of the effective value of the nacelle acceleration of the wind turbine generator set in a yaw state. The early warning and diagnosis unit determines that the wind turbine generator set has yaw vibration abnormality or determines that the cause of the yaw fault of the wind turbine generator set is yaw vibration abnormality when the first statistical feature value is less than a first threshold and the second statistical feature value is greater than a second threshold.

[0016] Optionally, the first statistical feature value is the variance of the effective value of the nacelle acceleration when the wind turbine is in a non-yaw state, and the second statistical feature value is the variance of the effective value of the nacelle acceleration when the wind turbine is in a yaw state. The early warning and diagnosis unit determines that the cause of the yaw fault of the wind turbine is tower resonance or yaw braking system failure when the wind turbine is stopped or started and yaws against the wind in the rotor speed range indicating that the wind turbine is in a stopped or started yaw against the wind state.

[0017] Optionally, the first statistical feature value is the variance of the effective value of the nacelle acceleration when the wind turbine is in a non-yaw state, and the second statistical feature value is the variance of the effective value of the nacelle acceleration when the wind turbine is in a yaw state. The early warning and diagnosis unit determines that the cause of the yaw fault of the wind turbine is unstable yaw torque or abnormal yaw noise in the rotor speed range indicating that the wind turbine is in a grid-connected power generation state, in response to the first statistical feature value being less than a first threshold and the second statistical feature value being greater than a third threshold.

[0018] According to another aspect of this disclosure, a computing system is provided that includes at least one computing device and at least one storage device for storing instructions, wherein the instructions, when executed by the at least one computing device, cause the at least one computing device to perform the yaw fault warning and diagnosis method for wind turbine generators as described above.

[0019] According to another aspect of this disclosure, a computer-readable storage medium is provided that stores instructions, wherein when the instructions are executed by at least one computing device, the at least one computing device causes the at least one computing device to perform the yaw fault warning and diagnosis method for wind turbine generators as described above.

[0020] According to another aspect of this disclosure, a wind turbine generator set is provided, the wind turbine generator set including the computing system described above.

[0021] By adopting this disclosure, the yaw vibration status of wind turbine generators can be monitored under all operating conditions, and the cause of the yaw fault and the corresponding operating conditions can be accurately diagnosed after the yaw fault occurs, without the need to install additional sensing equipment, thereby helping to improve the stability of the unit, reduce operation and maintenance costs and reduce power generation loss. Attached Figure Description

[0022] The above and / or other objects and advantages of this disclosure will become clearer from the following description of embodiments in conjunction with the accompanying drawings, wherein:

[0023] Figure 1This is a flowchart illustrating a method for early warning and diagnosis of yaw faults in a wind turbine generator set according to an exemplary embodiment of the present disclosure;

[0024] Figure 2 This is a flowchart illustrating a method for yaw fault early warning and diagnosis of a wind turbine generator set according to an embodiment of the present disclosure;

[0025] Figure 3 This is a block diagram illustrating a yaw fault warning and diagnosis device for a wind turbine generator set according to an exemplary embodiment of the present disclosure;

[0026] Figure 4 This is a block diagram illustrating a yaw fault warning and diagnosis device for a wind turbine generator set according to an embodiment of the present disclosure;

[0027] Figure 5 This diagram illustrates the diagnostic results of yaw brake damage and severe yaw pad wear based on yaw speed and yaw acceleration.

[0028] Figure 6 This is a schematic diagram illustrating the diagnostic results of verifying the loose mounting position of the vibration sensor based on yaw speed and yaw acceleration;

[0029] Figure 7 This is a schematic diagram illustrating the diagnostic results of verifying yaw noise based on yaw speed and yaw acceleration;

[0030] Figure 8 This is a block diagram illustrating a computing system including at least one computing device and at least one storage device of storage instructions according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0031] The following description, in conjunction with the accompanying drawings, provides specific embodiments to aid the reader in gaining a comprehensive understanding of the methods, apparatus, and / or systems described herein. However, upon understanding this disclosure, various changes, modifications, and equivalents of the methods, apparatus, and / or systems described herein will become apparent. For example, the order of operations described herein is merely illustrative and is not limited to those orders set forth herein, but may be altered as will become clear upon understanding this disclosure, except for operations that must occur in a specific order. Furthermore, for clarity and conciseness, descriptions of features known in the art may be omitted.

[0032] Excessive yaw acceleration can affect the safe operation and component lifespan of wind turbines, and frequent start-ups and shutdowns can also cause power generation losses. Therefore, it is necessary to provide timely early warning of abnormal yaw vibration to maintain the healthy operation of wind turbine generators in advance, and to accurately diagnose the cause of excessive yaw acceleration faults to improve operation and maintenance efficiency, thereby increasing power generation. To address the problems of existing methods for monitoring the vibration status of wind turbine generators during yaw, such as high cost, incompleteness, inaccuracy, or poor interpretability, this disclosure proposes a method and device for early warning and diagnosis of yaw faults in wind turbine generators. The method and device can monitor the vibration status of the generator in real time and accurately diagnose the cause of the yaw fault after it occurs.

[0033] Figure 1 This is a flowchart illustrating a method for early warning and diagnosis of yaw faults in a wind turbine generator set according to an exemplary embodiment of the present disclosure.

[0034] like Figure 1 As shown, in step S101, the operating data of the wind turbine generator set in the non-yaw state and the operating data of the wind turbine generator set in the yaw state are obtained.

[0035] In the example, operational data of the wind turbine generator set (including turbine status, yaw speed, active power, yaw residual pressure, yaw state, nacelle acceleration, wind speed, ambient temperature, etc.) can be collected. The collected data is cleaned and preprocessed to obtain operational data of the wind turbine generator set in a non-yaw state and operational data of the wind turbine generator set in a yaw state. For example, data on turbine status, yaw speed, active power, yaw residual pressure, yaw state, nacelle acceleration, wind speed, and ambient temperature within a predetermined time period can be read. The amount of data read can be adjusted according to the data collection frequency (for example, the amount of data read at one time can be at least 30,000 records). The turbine status refers to the current condition of the turbine and can include primary and secondary statuses. Primary statuses include grid connection, standby, maintenance, fault, and communication interruption. Secondary statuses include grid connection, load limiting (dispatch), load limiting (self), initialization, startup, low-wind shutdown, high-wind shutdown, power outage shutdown, low-wind standby, high-wind standby, shutdown process, cable disconnection process, on-site affected shutdown, off-site affected shutdown, standby, shutdown, maintenance, repair, network communication interruption, and turbine communication interruption. Next, data on extreme weather conditions such as strong winds and freezing can be filtered out based on turbine status, wind speed, and ambient temperature to select data for the normal operating period of the unit. For example, a turbine can typically be set to a maximum rated wind speed. When the wind speed exceeds the maximum rated wind speed (e.g., 30 m / s) for a predetermined time, shutdown is required to protect the unit; such weather conditions are referred to as extreme weather. In this example, data with wind speeds below the maximum rated wind speed can be filtered out based on wind speed. In the example, freezing extreme weather can refer to conditions where the temperature is below a specific temperature (e.g., zero degrees Celsius), and data during freezing extreme weather can be filtered out based on ambient temperature data.

[0036] After acquiring the operating data of the wind turbine generator set in both non-yaw and yaw states, in step S102, for each rotor speed range of the wind turbine generator set (for example, dividing the rotor speed into multiple ranges, such as [0,1], [1,2], [2,3], etc. in units of 1 rpm), a first statistical characteristic value and a second statistical characteristic value of the operating data of the wind turbine generator set in both non-yaw and yaw states are determined. In this example, the first statistical characteristic value may include the mean and variance of the effective values ​​of the nacelle acceleration and the median of the yaw residual pressure in the non-yaw state, and the second statistical characteristic value may include the mean and variance of the effective values ​​of the nacelle acceleration and the median of the yaw residual pressure in the yaw state.

[0037] In step S103, in response to at least one of the first and second statistical characteristic values ​​satisfying a preset condition, it is determined that the wind turbine generator set has experienced a yaw fault or the cause of the yaw fault is determined. That is, when the wind turbine generator set does not report a fault, abnormal nacelle acceleration vibration characteristics can be extracted for both yaw and non-yaw states to monitor the generator set's vibration state during yaw; and when a yaw acceleration exceeding the limit fault occurs, the abnormal nacelle acceleration vibration characteristics under yaw and non-yaw states can be compared and analyzed to accurately diagnose the cause of the yaw acceleration exceeding the limit fault.

[0038] In the example, if the wind turbine generator does not report a yaw fault, the wind turbine generator is determined to have an abnormal yaw pressure if at least one of the median yaw pressure of the wind turbine generator in the non-yaw state and the median yaw pressure of the wind turbine generator in the yaw state exceeds a preset range; the wind turbine generator is determined to have an accelerometer sensor malfunction if at least one of the mean effective values ​​of the nacelle acceleration of the wind turbine generator in the non-yaw state and the mean effective values ​​of the nacelle acceleration of the wind turbine generator in the yaw state are greater than a predetermined threshold; and the wind turbine generator is determined to have yaw vibration abnormality if the variance of the effective values ​​of the nacelle acceleration of the wind turbine generator in the non-yaw state is less than a first threshold and the variance of the effective values ​​of the nacelle acceleration of the wind turbine generator in the yaw state is greater than a second threshold.

[0039] Furthermore, in the event of a yaw fault reported by the wind turbine generator, if at least one of the median yaw residual pressure when the wind turbine generator is in a non-yaw state and the median yaw residual pressure when the wind turbine generator is in a yaw state exceeds a preset range, the cause of the yaw fault is determined to be abnormal yaw residual pressure; if at least one of the mean effective value of the nacelle acceleration when the wind turbine generator is in a non-yaw state and the mean effective value of the nacelle acceleration when the wind turbine generator is in a yaw state is greater than a predetermined threshold, the cause of the yaw fault is determined to be an acceleration sensor malfunction; if the variance of the effective value of the nacelle acceleration when the wind turbine generator is in a non-yaw state is less than a first threshold and the variance of the effective value of the nacelle acceleration when the wind turbine generator is in a yaw state is greater than a second threshold, a yaw fault is determined to have occurred in the wind turbine generator. The cause is abnormal yaw vibration and noise. For the rotor speed range indicating whether the wind turbine is in a stopped or started yaw-facing state, if the variance of the effective value of the nacelle acceleration is less than a first threshold when the wind turbine is in a non-yaw state and greater than a third threshold when the wind turbine is in a yaw state, the cause of the yaw fault is determined to be tower resonance or a yaw braking system malfunction when the wind turbine is stopped or started yaw-facing. For the rotor speed range indicating whether the wind turbine is in a grid-connected power generation state, if the variance of the effective value of the nacelle acceleration is less than a first threshold when the wind turbine is in a non-yaw state and greater than a third threshold when the wind turbine is in a yaw state, the cause of the yaw fault is determined to be unstable yaw torque or abnormal yaw noise. The predetermined thresholds mentioned here can be determined based on business experience and actual data performance. The first, second, and third thresholds can be determined by the distribution of previous data (for example, after calculating the statistical characteristics (including mean and standard deviation) of a large amount of normal data from the previous period, the range can be set as [mean - 3 times the standard deviation, mean + 3 times the standard deviation] according to the 3 sigma criterion). By adopting the above method, early warning of faults such as excessive yaw acceleration can be provided, which is beneficial to improving the safety and stability of wind turbine generators. Furthermore, diagnostic analysis after a fault is reported can provide strong support for on-site operation and maintenance personnel, thereby reducing the loss of power generation due to downtime.

[0040] Figure 2 This is a flowchart illustrating a method for yaw fault warning and diagnosis of a wind turbine generator set according to an embodiment of the present disclosure.

[0041] like Figure 2As shown, in step S201, data is read. As mentioned above, the fields read may include wind turbine status, yaw speed, active power, yaw residual pressure, yaw status, nacelle acceleration, wind speed, and ambient temperature data within a predetermined time period or a predetermined number of records. In step S202, the number of read data records is compared with a threshold N1 (for example, the threshold N1 can be set to 30,000 records based on the data acquisition frequency). If the number of read data records is greater than the threshold N1, the process proceeds to step S203; if the number of read data records is not greater than the threshold N1, the process ends. In step S203, data cleaning can be performed. For example, data from extreme weather conditions such as strong winds and freezing can be filtered based on wind turbine status, wind speed, and ambient temperature to select data from the normal operating period of the unit. In step S204, the number of filtered data entries is compared with the threshold N2 (for example, if the threshold N1 is set to 30,000 entries, the threshold N2 can be set to 15,000 entries). If the number of filtered data entries is greater than the threshold N2, proceed to step S205. If the number of filtered data entries is not greater than the threshold N2, the process ends.

[0042] In step S205, it is determined whether the crew reported a yaw acceleration exceeding the limit fault. If the crew did not report a yaw acceleration exceeding the limit fault, proceed to step S206. If the crew reported a yaw acceleration exceeding the limit fault, proceed to step S219. Figure 2 In this process, the branch corresponding to step S206 is used for yaw fault early warning of wind turbine generator set, and the branch corresponding to step S219 is used for yaw fault diagnosis of wind turbine generator set. The two branches will be explained in detail below.

[0043] In step S206, it is determined whether the unit is in a yaw state. If the unit is in a yaw state, proceed to step S207 to filter out data where the unit is in a yaw state; if the unit is not in a yaw state, proceed to step S210 to filter out data where the unit is not in a yaw state. For the filtered data where the unit is in a yaw state, in step S208, it is determined whether the number of data entries after filtering is greater than a data entry threshold N3 (for example, the data entry threshold N3 can be equal to 30% of the number of data entries generated by the unit in one day of operation). For the data where the unit is not in a yaw state, in step S211, it is determined whether the number of data entries after filtering is greater than a data entry threshold N4 (for example, the data entry threshold N4 can be equal to 30% of the number of data entries generated by the unit in one day of operation). If it is determined in step S208 that the number of data entries after filtering is greater than the data entry threshold N3, proceed to step S209. If it is determined in step S211 that the number of data entries after filtering is greater than the data entry threshold N4, proceed to step S212. If in step S208 it is determined that the number of filtered data entries is not greater than the data entry threshold N3, or if in step S211 it is determined that the number of filtered data entries is not greater than the data entry threshold N4, then the process ends. In step S209, the mean, variance, and median of the nacelle acceleration effective value and the yaw residual pressure (A1i, S1i, P1i) are calculated by speed compartment (i.e., for each rotor speed range of the wind turbine generator set (for example, the rotor speed is divided into multiple ranges, such as [0,1], [1,2], [2,3], etc. when divided in units of 1 rpm), the mean, variance, and median of the yaw residual pressure of the wind turbine generator set in the yaw state are determined in different speed ranges, where i = 1, 2, 3…j (j <= p11, p11 is the rated speed of the unit)). In step S212, the mean, variance, and median of the nacelle acceleration effective value and the yaw residual pressure are calculated by speed compartment (A2i, S2i, P2i) (that is, for each rotor speed range of the wind turbine generator set (for example, the rotor speed is divided into multiple ranges, such as [0,1], [1,2], [2,3], etc. when divided in units of 1 rpm), the mean, variance, and median of the yaw residual pressure of the wind turbine generator set in the non-yaw state are determined in different speed ranges, where i = 1,2,3…j (j <= p11, p11 is the rated speed of the unit)).In step S213, it is determined whether there is an error in the setting of the yaw residual pressure based on whether the median values P1i and P2i of the yaw residual pressure in the yaw state and non-yaw state of the unit (the hydraulic data at the start and stop of yaw can be excluded to avoid affecting the calculation of the yaw residual pressure value during normal yaw or wind alignment of the unit) are within a predetermined range. Here, the parameters p1i and p2i are the lower and upper limits of the yaw residual pressure when the unit is in the yaw state, and the parameters p3i and p4i are the lower and upper limits of the yaw residual pressure when the unit is in the non-yaw state. If it is determined in step S213 that there is no error in the setting of the yaw residual pressure (i.e., p1i < P1i < p2i and p3i < P2i < p4i), then proceed to step S215; otherwise, it is determined in step S214 that there is an abnormality in the yaw residual pressure. In step S215, it is determined whether the absolute values of the average value A1i of the effective value of the nacelle acceleration when the unit is in the yaw state and the average value A2i of the effective value of the nacelle acceleration when the unit is in the non-yaw state exceed p5i (which can be determined according to business experience and the performance of actual data), so as to determine whether there is an abnormality in the acceleration sensor. If the absolute values of A1i and A2i are both less than p5i, the method proceeds to step S217; otherwise, it is determined in step S216 that there is an abnormality in the acceleration sensor. In step S217, it is determined whether it satisfies that the variance S1i of the effective value of the nacelle acceleration when the unit is in the yaw state is greater than p6i and the variance S2i of the effective value of the nacelle acceleration when the unit is in the non-yaw state is less than p7i, where the parameters p6i and p7i can be determined by the distribution of previous data, for example, by the 3sigma criterion. If it is determined in step S217 that S1i > p6i and S2i < p7i, then it is determined in step S218 that there is a yaw vibration abnormal sound; otherwise, the process ends.

[0044] In step S219, it is determined whether the unit is in a yaw state. If the unit is in a yaw state, proceed to step S220 to filter out data where the unit is in a yaw state; if the unit is not in a yaw state, proceed to step S223 to filter out data where the unit is not in a yaw state. For the filtered data where the unit is in a yaw state, in step S221, it is determined whether the number of data entries after filtering is greater than a data entry threshold N5 (for example, the data entry threshold N5 can be equal to 30% of the number of data entries generated by the unit in one day of operation). For the data where the unit is not in a yaw state, in step S224, it is determined whether the number of data entries after filtering is greater than a data entry threshold N6 (for example, the data entry threshold N6 can be equal to 30% of the number of data entries generated by the unit in one day of operation). If it is determined in step S221 that the number of data entries after filtering is greater than the data entry threshold N5, proceed to step S222. If it is determined in step S224 that the number of data entries after filtering is greater than the data entry threshold N6, proceed to step S225. If in step S221 it is determined that the number of filtered data entries is not greater than the data entry threshold N5, or if in step S224 it is determined that the number of filtered data entries is not greater than the data entry threshold N6, then the process ends. In step S222, the mean, variance, and median of the nacelle acceleration effective value and the yaw residual pressure (A3i, S3i, P3i) are calculated by speed compartment (i.e., for each rotor speed range of the wind turbine generator set (for example, the rotor speed is divided into multiple ranges, such as [0,1], [1,2], [2,3], etc. in the case of division in units of 1 rpm), the mean, variance, and median of the yaw residual pressure of the wind turbine generator set in the yaw state are determined in different speed ranges, where i = 1,2,3…j (j <= p11, p11 is the rated speed of the unit)). In step S225, the mean, variance, and median of yaw residual pressure of the nacelle acceleration are calculated by speed compartment (A4i, S4i, P4i) (that is, for each rotor speed range of the wind turbine generator set (for example, the rotor speed is divided into multiple ranges, such as [0,1], [1,2], [2,3], etc. when divided in units of 1 rpm), the mean, variance, and median of yaw residual pressure of the nacelle acceleration of the wind turbine generator set in the non-yaw state are determined in different speed ranges, where i = 1,2,3…j (j <= p11, p11 is the rated speed of the unit)).In step S226, based on whether the median values P3i and P4i of the yaw residual pressure when the unit is in the yaw state and non-yaw state (hydraulic data at the yaw start and stop moments can be excluded to avoid affecting the calculation of the yaw residual pressure value during normal yaw or wind alignment of the unit) are within a predetermined range, it is determined whether there is an incorrect setting of the yaw residual pressure. Here, the parameters p1i and p2i are the lower and upper limits of the yaw residual pressure when the unit is in the yaw state, and the parameters p3i and p4i are the lower and upper limits of the yaw residual pressure when the unit is in the non-yaw state. If it is determined in step S226 that there is no incorrect setting of the yaw residual pressure (i.e., p1i < P1i < p2i and p3i < P2i < p4i), then proceed to step S227; otherwise, in step S214, it is determined that the reason for the yaw acceleration overrun fault is abnormal yaw residual pressure. In step S227, it is determined whether the absolute values of the mean A3i of the effective value of the nacelle acceleration when the unit is in the yaw state and the mean A4i of the effective value of the nacelle acceleration when the unit is in the non-yaw state exceed p5i, so as to determine whether the reason for the yaw acceleration overrun fault is an abnormal acceleration sensor. If the absolute values of A3i and A4i are both less than p5i, then the method proceeds to step S228; otherwise, in step S216, it is determined that the reason for the yaw acceleration overrun fault is an abnormal acceleration sensor. In step S228, it is determined whether when p9 = <i < p10 (i.e., the fan is in the shutdown, startup yaw wind alignment state), the variance S3i of the effective value of the nacelle acceleration when the unit is in the yaw state is greater than p8i and the variance S4i of the effective value of the nacelle acceleration when the unit is in the non-yaw state is less than p7i. If when p9 = <i < p10, the variance S3i of the effective value of the nacelle acceleration when the unit is in the yaw state is greater than p8i and the variance S4i of the effective value of the nacelle acceleration when the unit is in the non-yaw state is less than p7, then in step S231, it is determined that the reason for the yaw acceleration overrun fault is tower resonance or yaw brake system failure when the unit is in the shutdown, startup yaw wind alignment (mostly because the yaw hydraulic brake braking pressure is too large, causing tower resonance); otherwise, proceed to step S229. In step S229, it is determined whether when p10 = <i < p11 (i.e., the fan is in the grid-connected power generation state), the variance S3i of the effective value of the nacelle acceleration when the unit is in the yaw state is greater than p8i and the variance S4i of the effective value of the nacelle acceleration when the unit is in the non-yaw state is less than p7i. When p10 = <i < p11, the variance S3i of the effective value of the nacelle acceleration when the unit is in the yaw state is greater than p8i and the variance S4i of the effective value of the nacelle acceleration when the unit is in the non-yaw state is less than p7i, then in step S230, it is determined that the reason for the yaw acceleration overrun fault is yaw torque instability or yaw abnormal noise (the main reason for yaw abnormal noise is the unstable frictional movement between the yaw brake pads and the brake disc).Among them, parameters p6i, p7i, and p8i can be determined by the distribution of previous data (for example, by the 3 sigma criterion), while p9, p10, and p11 are the unit start-up and shutdown speeds, grid-connected generation speeds, and rated speeds, respectively, and can be determined according to the characteristics of different units.

[0045] Through the above process, based on the wind turbine's operating principle, the unit's operating data can be fully utilized to eliminate interference from factors such as extreme weather, yaw overpressure settings, and acceleration sensors. The characteristics of normal non-yaw vibrations and abnormal yaw vibrations can be extracted under different operating conditions, enabling full-condition monitoring of the unit's yaw vibration status. Simultaneously, after a yaw acceleration exceeding limit fault occurs, based on the unit's characteristics, a graded fault diagnosis of relevant components can be completed. Furthermore, it should be understood that the operations shown in this embodiment are merely examples, and other steps can be added or reduced. Figure 2 The steps shown are one or more, and the order of the different steps can be adjusted as needed.

[0046] Figure 3 This is a block diagram illustrating a yaw fault warning and diagnosis device for a wind turbine generator set according to an exemplary embodiment of the present disclosure.

[0047] like Figure 3 As shown, a yaw fault early warning and diagnosis device for a wind turbine generator set according to an exemplary embodiment of the present disclosure may include: a data acquisition unit 301, which acquires operating data of the wind turbine generator set in a non-yaw state and operating data in a yaw state; a statistical feature value determination unit 302, which determines a first statistical feature value of the operating data of the wind turbine generator set in a non-yaw state and a second statistical feature value of the operating data of the wind turbine generator set in a yaw state for each rotor speed range of the wind turbine generator set; and an early warning and diagnosis unit 303, which determines that a yaw fault has occurred in the wind turbine generator set or determines the cause of the yaw fault in the wind turbine generator set in response to at least one of the first and second statistical feature values ​​satisfying a preset condition. In the example, the first statistical feature value includes the mean and variance of the effective value of the nacelle acceleration of the wind turbine generator set in a non-yaw state and the median of the yaw residual pressure, and the second statistical feature value includes the mean and variance of the effective value of the nacelle acceleration of the wind turbine generator set in a yaw state and the median of the yaw residual pressure.

[0048] In the example, the early warning and diagnosis unit 303 may determine that the wind turbine has an abnormal yaw pressure or that the cause of a yaw fault is an abnormal yaw pressure if at least one of the median yaw pressure of the wind turbine in a non-yaw state and the median yaw pressure of the wind turbine in a yaw state exceeds a preset range. The early warning and diagnosis unit 303 may also determine that the wind turbine has an accelerometer malfunction or that the cause of a yaw fault is an accelerometer malfunction if at least one of the mean effective value of the nacelle acceleration of the wind turbine in a non-yaw state and the mean effective value of the nacelle acceleration of the wind turbine in a yaw state is greater than a predetermined threshold. Finally, the early warning and diagnosis unit 303 may determine that the wind turbine has yaw vibration or that the cause of a yaw fault is yaw vibration or abnormal noise if the variance of the effective value of the nacelle acceleration of the wind turbine in a non-yaw state is less than a first threshold and the variance of the effective value of the nacelle acceleration of the wind turbine in a yaw state is greater than a second threshold.

[0049] In addition, the early warning and diagnosis unit 303 can determine, for the rotor speed range indicating that the wind turbine is in a shutdown or start-up yaw-facing state, that the cause of the yaw fault in the wind turbine is tower resonance or yaw brake system failure when the wind turbine is in a non-yaw state and the variance of the effective value of the nacelle acceleration is less than a first threshold and the variance of the effective value of the nacelle acceleration is greater than a third threshold when the wind turbine is in a yaw state; the early warning and diagnosis unit 303 can also determine, for the rotor speed range indicating that the wind turbine is in a grid-connected power generation state, that the cause of the yaw fault in the wind turbine is wind turbine yaw torque instability or yaw abnormal noise when the rotor speed range indicates that the wind turbine is in a grid-connected power generation state and the variance of the effective value of the nacelle acceleration is less than a first threshold and the variance of the effective value of the nacelle acceleration is greater than a third threshold when the wind turbine is in a yaw state.

[0050] The above combination Figure 1 and Figure 2 The specific operations shown are respectively by Figure 3 The corresponding unit in the yaw fault early warning and diagnosis device 300 of the wind turbine generator set shown is responsible for the execution. Here, the specific operational details will not be elaborated.

[0051] Figure 4 This is a block diagram illustrating an example of a yaw fault warning and diagnostic device for a wind turbine generator set according to an embodiment of the present disclosure.

[0052] like Figure 4As shown, the yaw fault early warning and diagnosis device for wind turbine generator sets according to this embodiment may include a data input module 401, a parameter input module 402, a data cleaning and preprocessing module 403, a feature extraction and model building module 404, a yaw acceleration over-limit fault early warning module 405, a yaw acceleration over-limit fault diagnosis module 406, and a result display module 407. The data input module 401 may receive unit operating data (including but not limited to turbine status, yaw speed, active power, yaw residual pressure, yaw status, nacelle acceleration, wind speed, ambient temperature, etc.) from a SCADA data source, for example. The parameters received by the parameter input module 402 include data volume parameters and service parameters. The data volume parameters may include parameters for determining whether the model calculation is satisfied (e.g., the number of data entries threshold N1 to N6). The service parameters may include parameters for data filtering and early warning threshold parameters for determining whether to issue an early warning (e.g., parameters p1i to p8i). The data cleaning and preprocessing module 403 can clean and preprocess the data received through the data input module 401 based on the parameters provided by the parameter input module 402 (e.g., filtering out data from extreme weather conditions such as strong winds and freezing, and selecting data from the yaw state and the non-yaw state). The feature extraction and model building module 404 can calculate the mean and variance of the effective values ​​of cabin acceleration and the median of yaw residual pressure by engine speed compartment. The yaw acceleration over-limit fault early warning module 405 can perform, for example, Figure 2 The process branch corresponding to step S206 shown is used to achieve yaw acceleration status monitoring. The yaw acceleration over-limit fault diagnosis module 406 can execute, for example, as follows: Figure 2 The process branch shown corresponds to step S219, and is used to complete fault diagnosis analysis when an acceleration over-limit fault occurs. The result display module 407 can display the warning and diagnosis results.

[0053] It should be understood that, as Figure 4 The yaw fault warning and diagnosis device for the wind turbine generator shown is only an example, and the modules shown may be omitted or combined as needed.

[0054] Figure 5 This diagram illustrates the diagnostic results of yaw brake damage and severe yaw pad wear based on yaw speed and yaw acceleration. When the yaw brake is determined to be damaged and the yaw pads are severely worn using the yaw fault early warning and diagnostic device for wind turbine generators according to this disclosure, the yaw speed versus yaw acceleration curve shows an acceleration in the y-direction approaching -0.5 m / s². 2 Abnormal data (at 0m / s) 2 (The nearby data is normal).

[0055] Figure 6This is a schematic diagram illustrating the diagnostic results of verifying a loose vibration sensor mounting position based on yaw speed and yaw acceleration. When the yaw fault early warning and diagnostic device for wind turbine generators according to this disclosure indicates a loose vibration sensor mounting position, referring to the yaw speed vs. yaw acceleration curves, it can be seen that the acceleration in the x-direction is close to -0.3 m / s². 2 Abnormal data (at 0m / s) 2 (The nearby data is normal).

[0056] Figure 7 This is a schematic diagram illustrating the diagnostic results of verifying yaw abnormality based on yaw speed and yaw acceleration. When yaw abnormality is detected using the yaw fault early warning and diagnostic device for wind turbine generators according to this disclosure, referring to the yaw speed vs. yaw acceleration curve, it can be seen that the acceleration in the x-direction is close to 0.10 m / s². 2 Abnormal data (at 0m / s) 2 (Nearby data are normal), and the y-axis acceleration is close to -0.15 m / s². 2 Abnormal data (at 0m / s) 2 (The nearby data is normal).

[0057] Therefore, it can be verified that the yaw fault early warning and diagnosis method and device for wind turbine generators according to this disclosure can effectively provide early warning of yaw faults and diagnose the causes of faults.

[0058] Figure 8 This is a block diagram illustrating a computing system including at least one computing device and at least one storage device of storage instructions according to an exemplary embodiment of the present disclosure.

[0059] like Figure 8 As shown, the computing system 800 provided according to an exemplary embodiment of the present invention includes a computing device 801 and a storage device 802. The storage device 802 stores computer-executable instructions. When the computer-executable instructions are executed by the computing device 801, the yaw fault warning and diagnosis method of the wind turbine generator set described in any of the foregoing embodiments is executed.

[0060] The computing device 801 can be deployed in a server or client, or on a node device in a distributed network environment. Furthermore, the computing device 801 can be a PC, tablet, personal digital assistant, smartphone, web application, or other device capable of executing the aforementioned set of instructions. Here, the computing device is not necessarily a single computing device; it can be any collection of devices or circuits capable of executing the aforementioned instructions (or instruction sets) individually or in combination. The computing device can also be part of an integrated control system or system manager, or can be configured to interconnect locally or remotely (e.g., via wireless transmission) through an interface. In the computing device, the processor includes a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller, or a microprocessor. By way of example and not limitation, the processor also includes analog processors, digital processors, microprocessors, multi-core processors, processor arrays, network processors, etc.

[0061] According to another aspect of this disclosure, a computer-readable storage medium is provided that stores instructions, which, when executed by at least one computing device, cause the at least one computing device to perform the yaw fault warning and diagnosis method for a wind turbine generator as described above. The computer-readable storage medium includes magnetic media such as floppy disks and magnetic tapes, optical media (including optical disc (CD) ROMs and DVD ROMs), magneto-optical media such as floppy discs, hardware devices such as ROMs and RAMs designed for storing and executing program commands, and flash memory. The instructions may include language code executable by a computer using an interpreter and machine language code generated by a compiler.

[0062] According to another aspect of this disclosure, a wind turbine generator set is provided, the wind turbine generator set including the computing system described above.

[0063] By adopting this disclosure, the yaw vibration status of wind turbine generators can be monitored under all operating conditions, and the cause of the yaw fault and the corresponding operating conditions can be accurately diagnosed after the yaw fault occurs, without the need to install additional sensing equipment, thereby helping to improve the stability of the unit, reduce operation and maintenance costs and reduce power generation loss.

[0064] The processes, methods, or algorithms disclosed herein can be transmitted to, or implemented by, a processing device, controller, or computer, which may include any existing programmable electronic control unit or a dedicated electronic control unit. Similarly, the processes, methods, or algorithms can be stored in various forms as data and instructions executable by a controller or computer, including but not limited to information permanently stored on non-writable storage media (such as ROM devices) and information variablely stored on writable storage media (such as floppy disks, magnetic tapes, CDs, RAM devices, and other magnetic and optical media). The processes, methods, or algorithms can also be implemented in a software executable object. Optionally, the processes, methods, or algorithms can be implemented wholly or partially using suitable hardware components (such as ASICs, FPGAs, state machines, controllers, or other hardware components or devices) or a combination of hardware components, software components, and firmware components.

[0065] Although this disclosure includes specific examples, it will be apparent to those skilled in the art that various changes in form and detail may be made to these examples without departing from the spirit and scope of the claims and their equivalents. The examples described herein are to be considered merely for descriptive purposes and not for limiting purposes. The description of features or aspects in each example is to be considered applicable to similar features or aspects in other examples. Suitable results may be obtained if the described techniques are performed in a different order, and / or if components in the described system, architecture, apparatus, or circuit are combined in a different manner and / or if components in the described system, architecture, apparatus, or circuit are replaced or supplemented with other components or their equivalents. Therefore, the scope of this disclosure is not limited by the specific embodiments but by the claims and their equivalents, and all variations within the scope of the claims and their equivalents shall be construed as included in this disclosure.

Claims

1. A method for early warning and diagnosis of yaw fault in wind turbine generator sets, characterized in that, The method includes: The operating data of the wind turbine generator set in non-yaw state and operating data in yaw state are obtained. For each rotor speed range of the wind turbine generator set, a first statistical characteristic value and a second statistical characteristic value of the operating data of the wind turbine generator set in the non-yaw state are determined. The first statistical characteristic value includes the mean effective value of the nacelle acceleration and the median yaw residual pressure of the wind turbine generator set in the non-yaw state. The second statistical characteristic value includes the mean effective value of the nacelle acceleration and the median yaw residual pressure of the wind turbine generator set in the yaw state. If at least one of the mean effective value of nacelle acceleration when the wind turbine generator is in a non-yaw state and the mean effective value of nacelle acceleration when the wind turbine generator is in a yaw state is greater than a predetermined threshold, it is determined that the wind turbine generator has an acceleration sensor malfunction or that the cause of the yaw fault of the wind turbine generator is an acceleration sensor malfunction. If at least one of the median yaw residual pressure of the wind turbine generator set in a non-yaw state and the median yaw residual pressure of the wind turbine generator set in a yaw state exceeds a preset range, it is determined that the wind turbine generator set has an abnormal yaw residual pressure or that the cause of the yaw failure of the wind turbine generator set is an abnormal yaw residual pressure.

2. A method for early warning and diagnosis of yaw fault in wind turbine generator sets, characterized in that, The method includes: The operating data of the wind turbine generator set in non-yaw state and operating data in yaw state are obtained. For each rotor speed range of the wind turbine generator set, a first statistical characteristic value and a second statistical characteristic value of the operating data of the wind turbine generator set in the non-yaw state are determined. The first statistical characteristic value includes the variance of the effective value of the nacelle acceleration of the wind turbine generator set in the non-yaw state and the median of the yaw residual pressure of the wind turbine generator set in the non-yaw state. The second statistical characteristic value includes the variance of the effective value of the nacelle acceleration of the wind turbine generator set in the yaw state and the median of the yaw residual pressure of the wind turbine generator set in the yaw state. In response to the fact that the variance of the effective value of the nacelle acceleration of the wind turbine generator set in the non-yaw state is less than a first threshold and the variance of the effective value of the nacelle acceleration of the wind turbine generator set in the yaw state is greater than a second threshold, it is determined that the wind turbine generator set has yaw vibration abnormality or that the cause of the yaw fault of the wind turbine generator set is yaw vibration abnormality. If at least one of the median yaw residual pressure of the wind turbine generator set in a non-yaw state and the median yaw residual pressure of the wind turbine generator set in a yaw state exceeds a preset range, it is determined that the wind turbine generator set has an abnormal yaw residual pressure or that the cause of the yaw failure of the wind turbine generator set is an abnormal yaw residual pressure.

3. A method for early warning and diagnosis of yaw fault in wind turbine generator sets, characterized in that, The method includes: The operating data of the wind turbine generator set in non-yaw state and operating data in yaw state are obtained. For each rotor speed range of the wind turbine generator set, a first statistical characteristic value and a second statistical characteristic value of the operating data of the wind turbine generator set in the non-yaw state are determined. The first statistical characteristic value includes the variance of the effective value of the nacelle acceleration of the wind turbine generator set in the non-yaw state, and the second statistical characteristic value includes the variance of the effective value of the nacelle acceleration of the wind turbine generator set in the yaw state. For the rotor speed range indicating that the wind turbine is in a shutdown or start-up yaw-against-wind state, in response to the first statistical feature value being less than the first threshold and the second statistical feature value being greater than the third threshold, it is determined that the cause of the yaw fault of the wind turbine is tower resonance or yaw brake system failure when the wind turbine is shut down or started up and yaws against the wind.

4. The method according to claim 3, characterized in that, The first statistical characteristic value also includes the median yaw residual pressure of the wind turbine generator set in a non-yaw state, and the second statistical characteristic value also includes the median yaw residual pressure of the wind turbine generator set in a yaw state. The method further includes: in response to at least one of the median yaw residual pressure of the wind turbine generator set in a non-yaw state and the median yaw residual pressure of the wind turbine generator set in a yaw state exceeding a preset range, determining that the wind turbine generator set has an abnormal yaw residual pressure or determining that the cause of the yaw failure of the wind turbine generator set is an abnormal yaw residual pressure.

5. A method for early warning and diagnosis of yaw fault in wind turbine generator sets, characterized in that, The method includes: The operating data of the wind turbine generator set in non-yaw state and operating data in yaw state are obtained. For each rotor speed range of the wind turbine generator set, a first statistical characteristic value and a second statistical characteristic value of the operating data of the wind turbine generator set in the non-yaw state are determined. The first statistical characteristic value includes the variance of the effective value of the nacelle acceleration of the wind turbine generator set in the non-yaw state, and the second statistical characteristic value includes the variance of the effective value of the nacelle acceleration of the wind turbine generator set in the yaw state. For the rotor speed range indicating that the wind turbine is in grid-connected power generation state, in response to the first statistical feature value being less than the first threshold and the second statistical feature value being greater than the third threshold, it is determined that the cause of the yaw fault of the wind turbine is the instability of the yaw torque or the abnormal yaw noise.

6. The method according to claim 5, characterized in that, The first statistical characteristic value also includes the median yaw residual pressure of the wind turbine generator set in a non-yaw state, and the second statistical characteristic value also includes the median yaw residual pressure of the wind turbine generator set in a yaw state. The method further includes: in response to at least one of the median yaw residual pressure of the wind turbine generator set in a non-yaw state and the median yaw residual pressure of the wind turbine generator set in a yaw state exceeding a preset range, determining that the wind turbine generator set has an abnormal yaw residual pressure or determining that the cause of the yaw failure of the wind turbine generator set is an abnormal yaw residual pressure.

7. A yaw fault early warning and diagnostic device for wind turbine generator sets, characterized in that, The device includes a data acquisition unit, a statistical feature value determination unit, and an early warning and diagnosis unit, wherein the data acquisition unit, the statistical feature value determination unit, and the early warning and diagnosis unit are configured to perform the yaw fault early warning and diagnosis method for wind turbine generator sets according to any one of claims 1 to 6.

8. A computing system comprising at least one computing device and at least one storage device for storing instructions, characterized in that, When the instruction is executed by the at least one computing device, it causes the at least one computing device to perform the yaw fault warning and diagnosis method for wind turbine generators according to any one of claims 1 to 6.

9. A computer-readable storage medium for storing instructions, characterized in that, When the instruction is executed by at least one computing device, it causes the at least one computing device to perform the yaw fault warning and diagnosis method for wind turbine generators according to any one of claims 1 to 6.

10. A wind turbine generator set, characterized in that, Includes the computing system according to claim 8.

Images