Abnormality diagnosis method, device and storage medium for wind turbine generator system

Abstract

This disclosure provides a method, apparatus, and storage medium for anomaly diagnosis of wind turbine generator sets. The anomaly diagnosis method includes: acquiring operating data of the wind turbine generator set within a first time period as reference operating data; determining the actual modal frequency of a target component of the wind turbine generator set based on the reference operating data; acquiring operating data of the wind turbine generator set within a second time period as diagnostic operating data; and determining the cause of the anomaly and maintenance plan for the target component based on the diagnostic operating data and the actual modal frequency of the target component. This disclosure, by first determining a reliable actual modal frequency based on the reference operating data and then combining the diagnostic operating data and the actual modal frequency for anomaly diagnosis, can identify a clear cause of the anomaly and a corresponding maintenance plan, achieving more refined anomaly diagnosis. This allows for shutdown for inspection only when necessary, thereby improving diagnostic efficiency and reducing losses caused by frequent shutdowns.

Description

Technical Field

[0001] This disclosure relates to the field of wind power generation, and more specifically, to a method, apparatus, and storage medium for diagnosing anomalies in wind turbine generator sets. Background Technology

[0002] In the field of wind power generation, with the widespread application of large rotors, long flexible blades, and high-flexibility towers, the aeroelastic stability of wind turbine generators has received widespread attention, making the identification and protection against abnormal modal frequency amplitudes of the entire unit particularly important. Currently, existing technologies for identifying abnormal modal frequency amplitudes primarily rely on nacelle acceleration sensor signals and measured rotational speed signals. If the maximum spectral amplitude and its corresponding frequency value both exceed their respective preset values, an abnormal modal frequency amplitude fault is immediately reported, and the unit is shut down. Maintenance personnel then inspect the major components of the unit on-site, and restarting is only resumed after confirming no abnormalities. However, in reality, numerous factors can cause abnormal modal frequency amplitudes. Existing single diagnostic and maintenance strategies lead to frequent shutdowns and low efficiency. If the fault occurs at night or during severe weather, maintenance personnel may not be able to reach the site promptly, or back-end technical support personnel may be unavailable, severely impacting the unit's power generation. Summary of the Invention

[0003] Therefore, improving the efficiency of diagnosing modal frequency amplitude anomalies in wind turbine generators is of paramount importance.

[0004] In one general aspect, a method for diagnosing anomalies in a wind turbine generator set is provided. The method includes: acquiring operational data of the wind turbine generator set within a first time period as reference operational data; determining the actual modal frequency of a target component of the wind turbine generator set based on the reference operational data; acquiring operational data of the wind turbine generator set within a second time period as diagnostic operational data; and determining the cause of the anomaly and maintenance plan for the target component based on the diagnostic operational data and the actual modal frequency of the target component.

[0005] Optionally, determining the actual modal frequency of the target component of the wind turbine generator set based on the reference operating data includes: performing spectrum calculation on the reference operating data to obtain multiple reference frequency values ​​of the reference operating data and the amplitude corresponding to each of the multiple reference frequency values; determining the design frequency band of the target component based on the design modal frequency of the target component, wherein the design modal frequency of the target component is located within the design frequency band of the target component; selecting reference frequency values ​​that are within the design frequency band of the target component from the multiple reference frequency values ​​to obtain multiple candidate frequency values; and determining the candidate frequency value with the largest amplitude from the multiple candidate frequency values ​​as the actual modal frequency of the target component.

[0006] Optionally, determining the actual modal frequency of the target component of the wind turbine generator set based on the reference operating data includes: determining the actual modal frequency of the target component in each of the multiple first durations based on the reference operating data of the wind turbine generator set in multiple first durations; and determining the statistical value of the actual modal frequency of the target component in each of the multiple first durations as the actual modal frequency of the target component.

[0007] Optionally, the reference operating data includes at least one of the following: nacelle acceleration, rotational speed, torque control data, and pitch rate control data; wherein, when the reference operating data includes the nacelle acceleration, if the actual modal frequency of the target component includes the actual modal frequency within the impeller surface, then the nacelle acceleration includes lateral nacelle acceleration; if the actual modal frequency of the target component includes the actual modal frequency outside the impeller surface, then the nacelle acceleration includes aft and forward nacelle acceleration.

[0008] Optionally, acquiring the operating data of the wind turbine generator set within a second time period as diagnostic operating data includes: when the target component includes components other than the rotor, acquiring the first operating data and rotational speed of the wind turbine generator set within the second time period as the diagnostic operating data; determining the cause of the abnormality and maintenance plan of the target component based on the diagnostic operating data and the actual modal frequency of the target component includes: determining whether the target component has experienced a modal frequency amplitude abnormality based on the first operating data and the actual modal frequency of the target component; if it is determined that the target component has experienced a modal frequency amplitude abnormality, determining whether the target component has experienced resonance based on the rotational speed and a reference modal frequency, wherein the reference modal frequency is related to the actual modal frequency of the target component; and determining the cause of the abnormality and maintenance plan of the target component based on the determination result of whether the target component has experienced resonance.

[0009] Optionally, determining whether the target component resonates based on the rotational speed and the reference modal frequency includes: determining that the target component resonates when the maximum amplitude of the rotational speed is greater than a preset rotational speed amplitude, the frequency value corresponding to the maximum amplitude of the rotational speed, and the rotational speed harmonics are all close to the reference modal frequency, wherein the rotational speed harmonics are calculated based on the rotational speed.

[0010] Optionally, determining the cause of the abnormality and the operation and maintenance plan of the target component based on the determination result of whether the target component resonates includes: if the determination result indicates that the target component resonates, determining that the cause of the abnormality of the target component is a control strategy issue, and determining the operation and maintenance plan to output early warning information and adjust the control strategy.

[0011] Optionally, the actual modal frequencies of the target component include the actual first-order modal frequency and the actual second-order modal frequency of the target component. The step of determining the cause of the anomaly and the maintenance plan based on the determination result of whether the target component resonates includes: if it is determined that the target component has an abnormal first-order modal frequency amplitude, and the determination result indicates that the target component has not resonated, the cause of the anomaly is determined to be occasional complex wind conditions, and the maintenance plan is to output early warning information; if the number of occasional complex wind conditions occurring within a third time period exceeds a preset number, the cause of the anomaly is determined to be an excessive frequency of occasional complex wind conditions, and the maintenance plan is to shut down and conduct on-site inspection; if it is determined that the target component has an abnormal second-order modal frequency amplitude, and the determination result indicates that the target component has not resonated, the cause of the anomaly is determined to be a component structural issue, and the maintenance plan is to shut down and conduct on-site inspection.

[0012] Optionally, acquiring the operating data of the wind turbine generator set within a second time period as diagnostic operating data includes: when the target component includes the rotor, acquiring second operating data, environmental data, and pitch angle of the wind turbine generator set within the second time period as the diagnostic operating data; determining the cause of the rotor's abnormality and maintenance plan based on the diagnostic operating data and the actual modal frequency of the rotor includes: determining whether the rotor has experienced a modal frequency amplitude abnormality based on the second operating data and the actual modal frequency of the rotor; if it is determined that the rotor has experienced a modal frequency amplitude abnormality, determining the cause of the rotor's abnormality and maintenance plan based on the environmental data and the pitch angle.

[0013] Optionally, the environmental data includes ambient temperature, ambient humidity, and air density. The step of determining the cause of the impeller malfunction and the maintenance plan based on the environmental data and the blade pitch angle includes: if the ambient temperature is lower than a preset temperature, the ambient humidity is higher than a preset humidity, and the blade pitch angle is lower than a preset blade pitch angle, the cause of the impeller malfunction is determined to be impeller icing, and the maintenance plan is to shut down the machine until the ambient temperature is higher than the target temperature; if the air density is lower than a preset density and the blade pitch angle is lower than a preset blade pitch angle, the cause of the impeller malfunction is determined to be low air density, and the maintenance plan is to shut down the machine until the air density is higher than the target density, and adjust the control strategy after startup; if the cause of the impeller malfunction is not impeller icing or low air density, the cause of the impeller malfunction is determined to be blade damage or severe blade contamination, and the maintenance plan is to shut down the machine and conduct on-site inspection.

[0014] Optionally, determining the cause of the abnormality and maintenance plan of the target component based on the diagnostic operation data and the actual modal frequency of the target component further includes: when the maximum amplitude of the diagnostic operation data is greater than a preset amplitude and no cause of abnormality and maintenance plan for the modal frequency amplitude is determined, determining that the cause of the abnormality of the target component is a cause beyond the scope of cognition, and determining the maintenance plan as shutdown and on-site inspection.

[0015] In another general aspect, an anomaly diagnosis device for a wind turbine generator set is provided. The anomaly diagnosis device includes: an acquisition unit configured to acquire operating data of the wind turbine generator set within a first time period as reference operating data; a determination unit configured to determine the actual modal frequency of a target component of the wind turbine generator set based on the reference operating data; the acquisition unit is further configured to acquire operating data of the wind turbine generator set within a second time period as diagnostic operating data; and a diagnosis unit configured to determine the cause of the anomaly of the target component and the operation and maintenance plan based on the diagnostic operating data and the actual modal frequency of the target component.

[0016] Optionally, the determining unit is further configured to: perform spectrum calculation on the reference operating data to obtain multiple reference frequency values ​​of the reference operating data and the amplitude corresponding to each of the multiple reference frequency values; determine the design frequency band of the target component based on the design modal frequency of the target component, wherein the design modal frequency of the target component is located within the design frequency band of the target component; filter out reference frequency values ​​that are within the design frequency band of the target component from the multiple reference frequency values ​​to obtain multiple candidate frequency values; and determine the candidate frequency value with the largest amplitude from the multiple candidate frequency values ​​as the actual modal frequency of the target component.

[0017] Optionally, the determining unit is further configured to: determine the actual modal frequencies of the target component in the multiple first durations based on reference operating data of the wind turbine generator set in multiple first durations; and determine the statistical values ​​of the actual modal frequencies of the target component in the multiple first durations as the actual modal frequencies of the target component.

[0018] Optionally, the reference operating data includes at least one of the following: nacelle acceleration, rotational speed, torque control data, and pitch rate control data; wherein, when the reference operating data includes the nacelle acceleration, if the actual modal frequency of the target component includes the actual modal frequency within the impeller surface, then the nacelle acceleration includes lateral nacelle acceleration; if the actual modal frequency of the target component includes the actual modal frequency outside the impeller surface, then the nacelle acceleration includes aft and forward nacelle acceleration.

[0019] Optionally, the acquisition unit is further configured to acquire, when the target component includes components other than the impeller, the first operating data and rotational speed of the wind turbine generator set within the second time period, as the diagnostic operating data; the diagnostic unit is further configured to: determine whether the target component has experienced a modal frequency amplitude abnormality based on the first operating data and the actual modal frequency of the target component; if the target component is determined to have experienced a modal frequency amplitude abnormality, determine whether the target component has experienced resonance based on the rotational speed and a reference modal frequency, wherein the reference modal frequency is related to the actual modal frequency of the target component; and determine the cause of the abnormality and maintenance plan of the target component based on the determination result of whether the target component has experienced resonance.

[0020] Optionally, the diagnostic unit is further configured to determine that the target component resonates when the maximum amplitude of the rotational speed is greater than a preset rotational speed amplitude, the frequency value corresponding to the maximum amplitude of the rotational speed, and the rotational speed harmonics are all close to the reference modal frequency, wherein the rotational speed harmonics are calculated based on the rotational speed.

[0021] Optionally, the diagnostic unit is further configured to, when the determination result indicates that the target component is resonating, determine that the cause of the abnormality of the target component is a control strategy issue, and determine the operation and maintenance solution as outputting early warning information and adjusting the control strategy.

[0022] Optionally, the actual modal frequencies of the target component include the actual first-order modal frequencies and the actual second-order modal frequencies of the target component. The diagnostic unit is further configured to: determine that the target component has an abnormal first-order modal frequency amplitude and the determination result indicates that the target component has not resonated, determine that the cause of the abnormality of the target component is an occasional complex wind condition, and determine that the operation and maintenance plan is to output early warning information; determine that the cause of the abnormality of the target component is an excessive frequency of occasional complex wind conditions if the number of occurrences of occasional complex wind conditions exceeds a preset number within a third time period, and determine that the operation and maintenance plan is to shut down and conduct on-site inspection; determine that the target component has an abnormal second-order modal frequency amplitude and the determination result indicates that the target component has not resonated, determine that the cause of the abnormality of the target component is a component structural issue, and determine that the operation and maintenance plan is to shut down and conduct on-site inspection.

[0023] Optionally, the acquisition unit is further configured to acquire, when the target component includes the impeller, the second operating data, environmental data, and pitch angle of the wind turbine generator set within the second time period, as the diagnostic operating data; the diagnostic unit is further configured to: determine whether the impeller has experienced a modal frequency amplitude abnormality based on the second operating data and the actual modal frequency of the impeller; if it is determined that the impeller has experienced a modal frequency amplitude abnormality, determine the cause of the impeller abnormality and the operation and maintenance plan based on the environmental data and the pitch angle.

[0024] Optionally, the environmental data includes ambient temperature, ambient humidity, and air density. The diagnostic unit is further configured to: determine that the impeller malfunction is caused by impeller icing when the ambient temperature is lower than a preset temperature, the ambient humidity is higher than a preset humidity, and the propeller pitch angle is lower than a preset pitch angle; determine that the maintenance plan is to shut down the machine until the ambient temperature is higher than the target temperature when the ambient temperature is lower than a preset temperature and the propeller pitch angle is lower than a preset pitch angle; determine that the impeller malfunction is caused by low air density when the air density is lower than a preset density and the propeller pitch angle is lower than a preset pitch angle; determine that the maintenance plan is to shut down the machine until the air density is higher than the target density; and adjust the control strategy after startup. If the impeller malfunction is not caused by impeller icing or low air density, determine that the impeller malfunction is caused by blade damage or severe blade contamination; and determine that the maintenance plan is to shut down the machine and conduct on-site inspection.

[0025] Optionally, the diagnostic unit is further configured to: perform spectrum calculation on the diagnostic operation data to obtain multiple diagnostic frequency values ​​of the diagnostic operation data and the amplitude corresponding to each of the multiple diagnostic frequency values; if the maximum amplitude of the diagnostic operation data is greater than a preset amplitude and no abnormal cause or maintenance plan for the modal frequency amplitude is determined, the abnormal cause of the target component is determined to be a cause beyond the scope of cognition, and the maintenance plan is determined to be shutdown and on-site inspection.

[0026] In another general aspect, a computer-readable storage medium is provided, wherein when instructions in the computer-readable storage medium are executed by at least one processor, the at least one processor causes the at least one processor to perform the wind turbine generator anomaly diagnosis method as described above.

[0027] In another general aspect, a computer device is provided, comprising: at least one processor; at least one memory storing computer-executable instructions, wherein, when executed by the at least one processor, the computer-executable instructions cause the at least one processor to perform the abnormal diagnosis method for a wind turbine generator as described above.

[0028] This disclosure provides a method, device, and storage medium for diagnosing anomalies in wind turbine generator sets. Considering that after the generator set is installed, the actual modal frequencies of each component often deviate from the design modal frequencies of the corresponding components, there is an inherent disadvantage of unreliable diagnostic benchmarks. By first determining reliable actual modal frequencies based on reference operating data, and then combining diagnostic operating data and actual modal frequencies for anomaly diagnosis, a clear cause of the anomaly and corresponding operation and maintenance plan can be determined, achieving more detailed anomaly diagnosis. Consequently, the generator is only shut down for inspection when necessary, thereby improving diagnostic efficiency and reducing losses caused by frequent shutdowns.

[0029] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0030] Figure 1 This is a flowchart illustrating an anomaly diagnosis method for a wind turbine generator set according to an embodiment of the present disclosure;

[0031] Figure 2 This is a flowchart illustrating a unit actual mode frequency identification scheme according to a specific embodiment of the present disclosure;

[0032] Figure 3 This is a schematic diagram illustrating the root cause diagnosis process for first-order modal frequency amplitude anomalies of a tower according to a specific embodiment of the present disclosure;

[0033] Figure 4 This is a schematic diagram illustrating the root cause diagnosis process for tower second-order modal frequency amplitude anomalies according to a specific embodiment of the present disclosure;

[0034] Figure 5 This is a schematic diagram illustrating the root cause diagnosis process for impeller modal frequency amplitude anomalies according to a specific embodiment of the present disclosure;

[0035] Figure 6 This is a schematic diagram illustrating the process for identifying abnormal frequency amplitudes of generator units beyond the scope of cognition according to a specific embodiment of the present disclosure;

[0036] Figure 7 This is a block diagram illustrating an anomaly diagnosis device for a wind turbine generator set according to an embodiment of the present disclosure;

[0037] Figure 8 This is a block diagram illustrating a computer device according to an embodiment of the present disclosure. Detailed Implementation

[0038] The following detailed embodiments are provided to aid the reader in gaining a comprehensive understanding of the methods, apparatus, and / or systems described herein. However, various changes, modifications, and equivalents of the methods, apparatus, and / or systems described herein will become apparent upon understanding this disclosure. For example, the order of operations described herein is merely illustrative and is not limited to those orders set forth herein, but may be changed 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.

[0039] The features described herein may be implemented in different forms and should not be construed as limited to the examples described herein. Rather, the examples described herein are provided only to illustrate some of the many feasible ways of implementing the methods, apparatus, and / or systems described herein, which will become clear upon understanding the disclosure of this application.

[0040] As used herein, the term “and / or” includes any one of the associated listed items and any combination of any two or more.

[0041] Although terms such as “first,” “second,” and “third” may be used herein to describe various components, assemblies, regions, layers, or parts, these components, assemblies, regions, layers, or parts should not be limited by these terms. Rather, these terms are used only to distinguish one component, assembly, region, layer, or part from another. Thus, without departing from the teaching of the examples described herein, the first component, first assembly, first region, first layer, or first part referred to as the first component, first assembly, first region, first layer, or first part may also be referred to as the second component, second assembly, second region, second layer, or second part.

[0042] In the specification, when an element (such as a layer, region, or substrate) is described as being "on" another element, "connected to," or "bonded to" another element, the element may be directly "on" another element, directly "connected to," or "bonded to" the other element, or one or more other elements may be present in between. Conversely, when an element is described as being "directly on" another element, "directly connected to," or "directly bonded to" another element, no other elements may be present in between.

[0043] The terminology used herein is for the purpose of describing various examples only and is not intended to limit disclosure. Unless the context clearly indicates otherwise, the singular form is intended to include the plural form as well. The terms “comprising,” “including,” and “having” indicate the presence of the described features, quantities, operations, components, elements, and / or combinations thereof, but do not preclude the presence or addition of one or more other features, quantities, operations, components, elements, and / or combinations thereof.

[0044] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains upon understanding this disclosure. Unless expressly defined herein, terms (such as those defined in a general dictionary) shall be interpreted as having a meaning consistent with their meaning in the context of the relevant field and in this disclosure, and shall not be interpreted in an idealized or overly formalistic manner.

[0045] Furthermore, in the description of the examples, detailed descriptions of well-known related structures or functions will be omitted when it is believed that such detailed descriptions would lead to a vague interpretation of this disclosure.

[0046] Figure 1 This is a flowchart illustrating an anomaly diagnosis method for a wind turbine generator set according to an embodiment of the present disclosure.

[0047] Reference Figure 1 In step S101, the operating data of the wind turbine generator within a first time period is acquired as reference operating data. The first time period is a historical duration specifically used to acquire the reference operating data required to determine the actual modal frequency. As an example, the first time period can be between 100s and 200s, which is long enough to ensure the accuracy of spectrum calculation and thus extract the accurate actual modal frequency, but not too long, thus reasonably controlling the amount of calculation per operation and helping to reduce the computational load. It should be noted that, to ensure the reliability of spectrum calculation, the acquired operating data is only used as reference operating data if the wind turbine generator is continuously generating power within the first time period. If the continuous power generation time does not reach the first time period, the corresponding operating data is discarded and not used as reference operating data.

[0048] Optionally, the reference operating data includes at least one of the following: nacelle acceleration, speed, torque control data, and pitch rate control data. These operating data all reflect the vibration of the unit components, and the larger the amplitude of these data, the stronger the vibration energy. By using at least one of these operating data as reference operating data, the reliable determination of the actual modal frequencies can be ensured, and the range of operating data selection can be broadened, thus improving the flexibility of the scheme.

[0049] In step S102, the actual modal frequencies of the target components of the wind turbine generator set are determined based on reference operating data. As an example, the target components may include large components such as the tower and rotor, or smaller components such as the gearbox and generator; the selection depends on the specific object of interest in the actual diagnostic process.

[0050] Optionally, when the target component includes the impeller and the reference operating data includes nacelle acceleration, if the actual modal frequency of the target component includes the actual modal frequency within the impeller surface, then the nacelle acceleration includes lateral nacelle acceleration; if the actual modal frequency of the target component includes the actual modal frequency outside the impeller surface, then the nacelle acceleration includes aft and forward nacelle acceleration. Specifically, nacelle acceleration includes lateral nacelle acceleration and aft and forward acceleration. For the impeller, in-plane vibration mainly affects lateral nacelle acceleration, while out-of-plane vibration mainly affects aft and forward nacelle acceleration. Therefore, by selecting a matching nacelle acceleration direction based on whether the actual modal frequency of the target component of interest belongs to the impeller surface or not when the reference operating data includes nacelle acceleration, a more accurate determination of the actual modal frequency of interest can be ensured, providing a reliable basis for subsequent diagnostics.

[0051] Optionally, regarding the specific method for determining the actual modal frequency, step S102 includes: performing spectrum calculation on the reference operating data to obtain multiple reference frequency values ​​of the reference operating data and the amplitude (which can be called the spectrum amplitude) corresponding to each of the multiple reference frequency values; determining the design frequency band of the target component based on the design modal frequency of the target component, wherein the design modal frequency of the target component is located within the design frequency band of the target component; selecting reference frequency values ​​within the design frequency band of the target component from the multiple reference frequency values ​​to obtain multiple candidate frequency values; and determining the candidate frequency value with the largest amplitude from the multiple candidate frequency values ​​as the actual modal frequency of the target component. Considering that although there is a deviation between the actual modal frequency and the design modal frequency, the deviation is often not very large. By widening the frequency band to a certain extent based on the design modal frequency of the target component to obtain the design frequency band of the target component, and then finding the frequency value with the largest amplitude of the reference operating data in the design frequency band as the actual modal frequency, it is possible to search for the actual modal frequency near the design modal frequency by using the largest amplitude as a clue, thus ensuring the reliable determination of the actual modal frequency. It should be understood that the bandwidth of the design frequency band needs to be appropriate—large enough to encompass the actual modal frequencies, yet small enough to control the computational load. As an example, a coefficient 'a' greater than 0 and less than 1 can be configured to define a frequency band from (1-a) to (1+a) times the design modal frequency as the design frequency band, achieving equal searching of frequencies on both sides of the design frequency band. The value of coefficient 'a' can be obtained empirically and / or experimentally, and its range is, for example, 0.05 to 0.1.

[0052] Optionally, considering the limited accuracy of a single calculation, step S102 includes: determining the actual modal frequencies of the target component within each of the multiple first time periods based on reference operating data of the wind turbine generator set within multiple first time periods; and determining the statistical values ​​of the actual modal frequencies of the target component within each of the multiple first time periods as the actual modal frequencies of the target component. By determining the actual modal frequencies multiple times based on reference operating data for different time periods, and then using the statistical values ​​of these multiple actual modal frequencies as the final actual modal frequencies of the target component, the influence of random errors can be reduced, further improving the accuracy of the determined actual modal frequencies. As an example, the statistical values ​​are the mean, mode, and set quantiles (e.g., quartiles, upper 20% quantiles). This disclosure does not limit these values, and other statistical values ​​mentioned below are similar and will not be elaborated further.

[0053] It should be understood that the actual modal frequencies of the identified target components can be continuously updated to track changes in the actual modal frequencies as the unit experiences operational losses, or they can be updated periodically to reduce computational load. This disclosure does not impose any limitations on this. When performing subsequent diagnostic steps, the latest actual modal frequencies can be used directly.

[0054] In step S103, the operating data of the wind turbine generator set within the second time period is acquired as diagnostic operating data. It should be understood that, regarding time, the time period for acquiring the operating data here differs from the time period in step S101. The second time period may or may not be equal to the first time period; this disclosure does not impose any restrictions on this. Regarding the operating data, the specific operating data acquired here needs to be determined in conjunction with the target component being diagnosed. The operating data acquired in step S101 is for determining the actual modal frequency, so the two are not necessarily related and may be the same or different. Furthermore, similar to step S101, step S103 also only uses the acquired operating data as diagnostic operating data if the wind turbine generator set is continuously generating power within the second time period. If the continuous power generation time does not reach the second time period, the corresponding operating data is discarded and not used as diagnostic operating data.

[0055] In step S104, based on the diagnostic operation data and the actual modal frequencies of the target component, the cause of the anomaly and the maintenance plan for the target component are determined. The specific diagnostic methods differ for different target components, or for different modal frequencies of the same target component, and will be described in detail below.

[0056] The anomaly diagnosis method for wind turbine generator sets disclosed herein takes into account that after the generator set is installed, there is often a certain deviation between the actual modal frequency of each component and the design modal frequency of the corresponding component, which naturally has the disadvantage of unreliable diagnostic benchmark. By first determining the reliable actual modal frequency based on reference operating data, and then combining the diagnostic operating data and the actual modal frequency to perform anomaly diagnosis, a clear cause of the anomaly and the corresponding operation and maintenance plan can be determined, realizing more detailed anomaly diagnosis. As a result, the generator is only shut down for inspection when necessary, thereby improving diagnostic efficiency and reducing the losses caused by frequent shutdowns.

[0057] The following section will provide a detailed introduction to the diagnostic methods for different target components and the diagnostic operating data used. Simply put, as a large, exposed rotating component, the impeller's vibration mode differs from other components, and therefore its diagnostic methods also differ. Thus, the following text will be divided into two parts, introducing the impeller and other components separately.

[0058] In some embodiments, step S103 includes: when the target component includes components other than the rotor, acquiring first operating data and rotational speed of the wind turbine generator set within a second time period as diagnostic operating data. In other words, it is first determined that the rotational speed needs to be acquired, and other operating data also needs to be acquired, denoted as the first operating data. As an example, the first operating data includes at least one of the following: nacelle acceleration, torque control data, and pitch rate control data. Regarding nacelle acceleration, since this is for components other than the rotor, it is not necessary to distinguish between lateral nacelle acceleration and left and right nacelle acceleration; one or both can be selected. Step S104 includes: determining whether the target component has experienced a modal frequency amplitude anomaly based on the first operating data and the actual modal frequency of the target component; if it is determined that the target component has experienced a modal frequency amplitude anomaly, determining whether the target component has experienced resonance based on the rotational speed and a reference modal frequency, wherein the reference modal frequency is related to the actual modal frequency of the target component; and determining the cause of the anomaly and maintenance plan for the target component based on the determination result of whether the target component has experienced resonance. Analysis revealed that when a target component experiences abnormal modal frequency amplitude, resonance is often the cause if it is due to an inappropriate control strategy; otherwise, other reasons exist. Therefore, further determining whether resonance occurs when an abnormal modal frequency amplitude is confirmed provides a reliable basis for troubleshooting the cause of the anomaly, helps clarify the cause and corresponding maintenance plan, and improves diagnostic efficiency. Specifically, to perform vibration-related calculations, the acquired first operating data and rotational speed need to be subjected to spectrum calculations to obtain multiple pairs of associated frequency and amplitude values. This calculation is part of data preparation and can be categorized into either step S103 or step S104, without affecting the substantive content of this disclosure.

[0059] Regarding the three sub-steps in step S104, optionally, when determining whether the target component has experienced a modal frequency amplitude anomaly, multiple pairs of associated frequency values ​​and amplitudes from the first operating data can be used. First, determine the maximum spectral amplitude of the first operating data, then determine whether the maximum spectral amplitude is greater than the first operating data amplitude threshold b. If so, it indicates that a large vibration has occurred. At this point, determine whether the frequency value corresponding to the maximum spectral amplitude is close to the actual modal frequency of the target component determined in step S102. If so, it is determined that the target component has experienced a modal frequency amplitude anomaly. It should be understood that the first operating data amplitude threshold b can be determined experimentally. If the maximum spectral amplitude of the first operating data is less than or equal to the first operating data amplitude threshold b, or if, although the maximum spectral amplitude of the first operating data is greater than the first operating data amplitude threshold b, the frequency value corresponding to the maximum spectral amplitude is far from the actual modal frequency of the target component determined in step S102, it is determined that the target component has not experienced a modal frequency amplitude anomaly. As an example, when determining whether the frequency value corresponding to the maximum spectral amplitude is close to the actual modal frequency of the target component, the method for determining the design frequency band in step S102 can be referenced. This involves determining a frequency band from (1-c) to (1+c) times the actual modal frequency of the target component, where c is a coefficient greater than 0 and less than 1. If the frequency value corresponding to the maximum spectral amplitude is within this frequency band, then the frequency value corresponding to the maximum spectral amplitude is determined to be close to the actual modal frequency of the target component; otherwise, the frequency value corresponding to the maximum spectral amplitude is determined to be far from the actual modal frequency of the target component. Similar to the prior art, to determine if a modal frequency amplitude anomaly has occurred, the condition that the maximum spectral amplitude is greater than a corresponding threshold must be met. However, regarding frequency, the prior art only requires that the frequency value corresponding to the maximum spectral amplitude be greater than the corresponding threshold, while this disclosure requires that the frequency value corresponding to the maximum spectral amplitude be close to the actual modal frequency of the target component. Since this disclosure determines a relatively accurate actual modal frequency in step S102, it can support the use of this condition, thereby narrowing the frequency condition range, helping to reduce the risk of misjudgment, and improving the accuracy of the judgment. It should be noted that when the first operating data uses more than two data points, such as using lateral nacelle acceleration and torque control data simultaneously, it is possible to first determine whether a modal frequency amplitude anomaly has occurred for each data point, and then summarize the judgment results of each data point. For example, it can be determined that a modal frequency amplitude anomaly has occurred when at least one data point has a judgment result of "yes", or it can be determined that a modal frequency amplitude anomaly has occurred when all data points have a judgment result of "yes". This disclosure does not impose any restrictions on this.

[0060] Optionally, when determining whether a target component resonates, multiple pairs of associated frequency and amplitude values ​​of rotational speed, as well as rotational speed harmonics, can be used. Rotational speed harmonics can be calculated based on rotational speed; this calculation, like spectrum calculation, is part of data preparation. Specifically, due to the large amount of acquired rotational speed data, the statistical values ​​of the acquired rotational speeds can be determined first, and then the rotational speed harmonics can be calculated based on these statistical values. The frequency obtained by dividing the rotational speed by 60 is the first harmonic of the rotational speed, and the product of the first harmonic of the rotational speed and n is the nth harmonic of the rotational speed. Here, at least one specified harmonic of the rotational speed can be used, such as the first harmonic and the second harmonic; this disclosure does not impose any limitations on this. Resonance of the target component is determined when the maximum amplitude of the rotational speed is greater than a preset rotational speed amplitude, the frequency value corresponding to the maximum amplitude of the rotational speed, and the rotational speed harmonics are all close to the reference modal frequency. Here, the maximum amplitude of the rotational speed spectrum being greater than the preset rotational speed amplitude indicates that the entire machine has experienced significant vibration during impeller rotation, and the frequency value corresponding to the maximum amplitude of the spectrum reflects the frequency at which the vibration occurs. Rotational speed harmonics are also commonly used in vibration studies to determine the cause of increased machine vibration. By simultaneously using the frequency value corresponding to the maximum amplitude of the rotational speed and the rotational speed harmonic during frequency determination, resonance of the target component can be reliably determined when both are close to a reference modal frequency related to the actual modal frequency of the target component, ensuring the accuracy of the diagnosis. It should be understood that when determining whether the frequency value corresponding to the maximum amplitude of the rotational speed is close to the reference modal frequency, and when determining whether the rotational speed harmonic is close to the reference modal frequency, the scheme used above for determining whether the frequency value corresponding to the maximum amplitude of the spectrum of the first operating data is close to the actual modal frequency of the target component can be referenced. A frequency band is constructed based on the reference modal frequency and a coefficient greater than 0 and less than 1, which will not be elaborated further here. As an example, the actual modal frequency of the target component can be directly used as the reference modal frequency. Furthermore, since the premise for determining whether the target component resonates is that the target component has experienced a modal frequency amplitude anomaly, the frequency value corresponding to the maximum amplitude of the spectrum of the first operating data used in determining whether the target component has experienced a modal frequency amplitude anomaly must be close to the actual modal frequency of the target component, and therefore this frequency value can also be used. This disclosure does not impose any restrictions on this. It should be noted that as the wind turbine generator sets are in operation, the structure of the units may gradually change. Therefore, as mentioned earlier, the actual modal frequencies of the target components can be continuously updated. The frequency value corresponding to the maximum spectral amplitude of the first operating data may be closer to the actual modal frequency at the current moment, so it is advisable to prioritize using this frequency value.

[0061] Optionally, when determining the cause of the target component's anomaly and the corresponding maintenance plan based on the determination of whether resonance has occurred, if the determination indicates that resonance has occurred, the cause of the anomaly is determined to be a control strategy issue, and the maintenance plan is determined to be outputting early warning information and adjusting the control strategy. Since resonance occurs during impeller rotation and is strongly correlated with rotational speed, which is directly determined by the control strategy, determining that resonance has occurred clearly indicates a control strategy issue. By outputting early warning information and adjusting the control strategy, the anomaly can be eliminated without shutting down the system, effectively reducing unnecessary downtime losses and improving diagnostic efficiency.

[0062] Optionally, the actual modal frequencies of the target component include the actual first-order modal frequencies and the actual second-order modal frequencies of the target component. Accordingly, when determining the cause of the target component's anomaly and the maintenance plan based on the determination of whether the target component resonates, if it is determined that the target component has an abnormal first-order modal frequency amplitude and the determination result indicates that the target component has not resonated, then the cause of the target component's anomaly is determined to be occasional complex wind conditions, and the maintenance plan is determined to be outputting early warning information; if the number of occasional complex wind conditions occurring within the third time period exceeds a preset number, then the cause of the target component's anomaly is determined to be an excessive frequency of occasional complex wind conditions, and the maintenance plan is determined to be shutdown and on-site inspection; if it is determined that the target component has an abnormal second-order modal frequency amplitude and the determination result indicates that the target component has not resonated, then the cause of the target component's anomaly is determined to be a component structural issue, and the maintenance plan is determined to be shutdown and on-site inspection. If resonance has not occurred, it can be determined that the cause of the anomaly is not due to the control strategy. By analyzing the amplitude anomalies of different modal frequencies, the corresponding causes can be identified based on the actual situation. This further clarifies the causes of anomalies when resonance has not occurred and allows for the determination of appropriate operation and maintenance solutions, ensuring the comprehensiveness of the diagnosis and improving diagnostic efficiency. Specifically, analysis revealed that occasional complex wind conditions can cause non-resonant first-order modal frequency amplitude anomalies, so corresponding anomaly cause diagnosis can be performed, and no intervention is required at this time. However, if the frequency of occasional complex wind conditions is too high, exceeding the normal frequency, it is necessary to shut down the system for further inspection and analysis to determine the specific cause of the anomaly. Occasional complex wind conditions often do not cause non-resonant second-order modal frequency amplitude anomalies; therefore, in this case, anomalies in the component structure should be considered, requiring shutdown for further inspection and analysis.

[0063] It should be noted that when the actual modal frequencies of the target component include at least two actual modal frequencies, such as the case mentioned earlier which includes the actual first-order modal frequency and the actual second-order modal frequency, although the diagnostic schemes for different modal frequencies have been described together for ease of explanation, resulting in a certain order of description, in actual execution, independent diagnosis can be performed for each modal frequency in step S104. That is, the diagnosis of different modal frequencies does not affect each other and can be performed simultaneously. Accordingly, the specific parameter values ​​used in different diagnostic processes can be different. It should be understood that the so-called independent diagnosis, taking the diagnosis of abnormal first-order modal frequencies of components other than the impeller as an example, means that in step S104, the target component is determined to have an abnormal first-order modal frequency amplitude by referring to the actual first-order modal frequency. If it is determined that the target component has an abnormal first-order modal frequency amplitude, the preset rotational speed amplitude corresponding to the first-order modal frequency and the reference modal frequency related to the actual first-order modal frequency are used to determine whether resonance has occurred, thereby determining the cause of the abnormality and the operation and maintenance plan. Similarly, the diagnostic method for the impeller, which will be described below, is performed independently, just like the diagnostic method for other components.

[0064] For the execution of steps S101 to S03, as an example, the actual modal frequencies of each target component can be determined uniformly in steps S101 and S102. Then, in step S103, the diagnostic operation data required for each target component can be uniformly obtained, and data preparation work, including spectrum calculation, can be performed to obtain a dataset. In step S104, the diagnostic process for each modal frequency of each target component only needs to be run independently, and the required data can be obtained from the dataset at the starting point of the process, which helps to reduce the amount of repetitive calculation.

[0065] In some embodiments, step S103 includes: when the target component includes the rotor, acquiring second operating data, environmental data, and pitch angle of the wind turbine generator set within a second time period as diagnostic operating data. In other words, it is first determined that environmental data and pitch angle need to be acquired, and other operating data also need to be acquired, referred to as second operating data. As an example, the second operating data includes at least one of the following: nacelle acceleration, speed, torque control data, and pitch rate control data. It should be noted that although the available data for the second operating data is the same as the available data for the reference operating data, different data may be used during execution, and they are not related to each other. Step S104 includes: determining whether the rotor has experienced a modal frequency amplitude anomaly based on the second operating data and the actual modal frequency of the rotor; if it is determined that the rotor has experienced a modal frequency amplitude anomaly, determining the cause of the rotor anomaly and the operation and maintenance plan based on the environmental data and pitch angle. The step of using the second operating data to refer to the actual modal frequency of the rotor to determine whether the rotor has experienced a modal frequency amplitude anomaly is similar to the step of determining whether components other than the rotor have experienced a modal frequency amplitude anomaly, and will not be elaborated here. When it is determined that the modal frequency amplitude of the impeller is abnormal, considering that the abnormal vibration of the impeller is often caused by problems with the blade itself or environmental factors, by analyzing environmental data and pitch angle, the cause of the abnormality can be reliably identified, and then the corresponding operation and maintenance plan can be determined, which helps to improve diagnostic efficiency.

[0066] Optionally, regarding how to diagnose the cause of the anomaly and determine the corresponding operation and maintenance plan, the environmental data used includes ambient temperature, ambient humidity, and air density. Based on the environmental data and the blade pitch angle, the steps to determine the cause of the impeller anomaly and the operation and maintenance plan include: if the ambient temperature is lower than the preset temperature, the ambient humidity is higher than the preset humidity, and the blade pitch angle is lower than the preset blade pitch angle, the cause of the impeller anomaly is determined to be impeller icing, and the operation and maintenance plan is to shut down the machine until the ambient temperature is higher than the target temperature; if the air density is lower than the preset density and the blade pitch angle is lower than the preset blade pitch angle, the cause of the impeller anomaly is determined to be low air density, and the operation and maintenance plan is to shut down the machine until the air density is higher than the target density, and adjust the control strategy after restarting; if the cause of the impeller anomaly is not impeller icing or low air density, the cause of the impeller anomaly is determined to be blade damage or severe blade contamination, and the operation and maintenance plan is to shut down the machine and conduct on-site inspection. In general, abnormal impeller vibration is often caused by problems with the blades themselves or by environmental factors. Environmental factors mainly include impeller icing, severe contamination of the blade surface due to deposits, and low air density caused by low ambient temperature leading to blade stall and instability. Analysis shows that impeller icing indicates low ambient temperature and high humidity, while blade stall and instability due to low air density indicates low ambient air density. Both of these situations can be analyzed and determined by monitoring environmental data, and such anomalies usually subside on their own after environmental improvements. Blade problems and severe blade contamination are relatively difficult to detect directly and require manual maintenance. Therefore, by classifying impeller anomalies into three categories—impeller icing, low air density, and blade damage or severe blade contamination—and using environmental data to clarify the first two causes, while categorizing other causes as the third, we can reasonably determine the causes of anomalies and corresponding maintenance solutions with less computation, thus improving the efficiency of anomaly diagnosis. Meanwhile, when combining environmental data to clarify the causes of the first two anomalies, considering that when the wind energy absorbed by the unit is significantly reduced, the control will adjust the pitch angle to capture more wind energy, so an excessively small pitch angle can indicate poor wind energy absorption. By adding a judgment condition that the pitch angle is less than the preset pitch angle, it is possible to determine whether the poor wind energy absorption is caused by environmental factors, and then determine the specific environmental anomaly cause based on the specific environmental data, ensuring the reliability of the cause investigation. In addition, for cases where the anomaly is caused by low air density, considering that air density is related to the control strategy, by adding a part to adjust the control strategy after startup to its operation and maintenance plan, the operational stability after shutdown and restart can be ensured.

[0067] In some embodiments, step S104 further includes: when the maximum amplitude of the diagnostic operating data is greater than a preset amplitude, and the cause of the abnormal modal frequency amplitude and maintenance plan have not been determined, the cause of the abnormality of the target component is determined to be beyond the scope of understanding, and the maintenance plan is determined to be shutdown and on-site inspection. When both the detection and cause determination of the abnormal modal frequency amplitude of the target component are performed simultaneously, by further enriching the plan, situations where the amplitude is too large but the cause of the abnormal modal frequency amplitude has not been diagnosed—that is, situations where the maximum amplitude of the diagnostic operating data is greater than a preset amplitude, but the frequency value corresponding to the maximum amplitude is not within the actual modal frequency and speed multiple of the target component of the unit's main focus—are still considered abnormal, and the cause of the abnormality is classified as beyond the scope of understanding. Analysis suggests that the cause of such an abnormality may be damage to a major component of the unit, causing changes in the actual modal frequency, etc. Shutdown inspection can ensure a comprehensive identification of the abnormal situation while accurately identifying the cause of the abnormality, thus helping to ensure the safe operation of the wind turbine generator set. It should be understood that when multiple data points are selected for diagnostic operation, such as simultaneously selecting nacelle acceleration and rotational speed, the preset amplitudes corresponding to different data points may differ and can be determined through testing. The maximum amplitude of any one data point can be considered greater than its corresponding preset amplitude. Alternatively, the maximum amplitude of all data points can be considered greater than their respective preset amplitudes; this disclosure does not impose any limitations on this. It should also be understood that since the diagnosis of causes beyond the scope of knowledge requires consideration of the diagnostic results of modal frequency amplitude anomalies, this diagnostic process can be slightly later than the diagnostic process for modal frequency amplitude anomalies of the target component.

[0068] Next, combine Figures 2 to 6 This invention introduces a method for diagnosing anomalies in a wind turbine generator set according to a specific embodiment of the present disclosure.

[0069] This specific embodiment includes five parts: a scheme for identifying the actual modal frequencies of the generator unit, a scheme for diagnosing and maintaining the root causes of tower first-order modal frequency amplitude anomalies, a scheme for diagnosing and maintaining the root causes of tower second-order modal frequency amplitude anomalies, a scheme for diagnosing and maintaining the root causes of impeller modal frequency amplitude anomalies, and a scheme for identifying and maintaining frequency amplitude anomalies of generator units that are beyond the scope of understanding. The impeller modal frequency amplitude anomaly is illustrated using the in-plane modal frequency as an example; the root cause diagnosis and maintenance scheme for out-of-plane modal frequency amplitude anomalies is the same as that for the in-plane modal frequency anomalies. The reason for identifying the actual modal frequencies of the generator unit is to consider the certain deviation between the design modal frequencies of the generator unit and the actual modal frequencies of the entire unit after installation. In this specific embodiment, since it is necessary to diagnose impeller in-plane modal frequency amplitude anomalies, the lateral nacelle acceleration is selected as the reference operating data; regarding the diagnostic operating data, the first operating data is the nacelle acceleration (either lateral nacelle acceleration or aft and rear nacelle acceleration can be used), and the second operating data is the rotational speed.

[0070] Reference Figure 2 The actual modal frequency identification scheme for the unit is as follows: First, using time t1 as a data unit, the lateral nacelle acceleration during unit power generation is continuously acquired. This means that if the continuous power generation time does not reach time t1, the acquired data is discarded, and the same applies below. Next, spectrum calculation is performed on each data unit, and the frequency band from (1-a) to (1+a) times the design modal frequency is extracted. The design modal frequencies include the first-order design modal frequency of the tower, the second-order design modal frequency of the tower, the first-order design modal frequency in the impeller plane, the second-order design modal frequency in the impeller plane, and the third-order design modal frequency in the impeller plane. The frequency value corresponding to the largest amplitude in the frequency band is taken as the actual modal frequency extracted for this data unit. The actual modal frequencies include the first-order actual modal frequency of the tower, the second-order actual modal frequency of the tower, the first-order actual modal frequency in the impeller plane, the second-order actual modal frequency in the impeller plane, and the third-order actual modal frequency in the impeller plane. The actual modal frequencies extracted for each data unit are then stored. Once the number of data units reaches n, the average value of the actual modal frequencies extracted from the n data units is calculated as the identified actual modal frequency. Here, t1 ranges from 100s to 200s, a ranges from 0.05 to 0.1, and n ranges from 100 to above.

[0071] Reference Figure 3The root cause diagnosis and maintenance plan for the tower's first-order modal frequency amplitude anomaly is as follows: First, using t2 as a data unit, continuously acquire the nacelle acceleration and rotational speed under generator operation. Then, prepare the data, including performing spectrum calculations on the nacelle acceleration and rotational speed, calculating the average rotational speed, and calculating the rotational speed harmonics based on the average rotational speed. Next, determine whether the following conditions are met simultaneously: the maximum amplitude of the nacelle acceleration spectrum is greater than b, and the frequency value corresponding to the maximum amplitude of the nacelle acceleration spectrum is within the frequency band of (1-c) to (1+c) times the actual first-order modal frequency of the tower. If so, it is determined that the tower has experienced a first-order modal frequency amplitude anomaly. Continue to determine whether the following conditions are met simultaneously: the maximum amplitude of the rotational speed spectrum is greater than d, and the ratio of the frequency value corresponding to the maximum amplitude of the rotational speed spectrum to the frequency value corresponding to the maximum amplitude of the nacelle acceleration spectrum, and the ratio of the rotational speed harmonics to the frequency value corresponding to the maximum amplitude of the nacelle acceleration spectrum are both within the range of (1-e) to (1+e). If yes, resonance has occurred, the cause of the anomaly is a control strategy issue, and the maintenance plan is to output warning information without shutting down the system. No on-site inspection by maintenance personnel is required, but feedback to R&D personnel is needed for control strategy optimization. If no resonance has occurred, the cause of the anomaly is occasional complex wind conditions, and the maintenance plan is to output warning information without shutting down the system. If the number of warnings within time t3 is greater than f, the cause of the anomaly is further determined to be an excessive frequency of occasional complex wind conditions, exceeding the usual frequency of occasional complex wind conditions. The maintenance plan is to perform a fault shutdown, restarting the system only after maintenance personnel have checked major components and found no abnormalities, and simultaneously sending operational data to R&D personnel for further root cause analysis. Specifically, the value of t2 is consistent with t1, b can be 0.04g (g is gravitational acceleration), c and e can be 0.05, d ranges from 0.2 RPM (Revolutions Per Minute) to 0.5 RPM, t3 can be 24 hours, and f ranges from 3 to 5.

[0072] Reference Figure 4 The root cause diagnosis and maintenance plan for tower second-order modal frequency amplitude anomalies is similar to that for tower first-order modal frequency amplitude anomalies. The difference lies in that, when a second-order modal frequency amplitude anomaly is confirmed in the tower without resonance, the cause is attributed to component structure issues, specifically the tower system structure. The maintenance plan is the same as when the anomaly is caused by occasional, complex wind conditions exceeding frequency limits: a fault shutdown is initiated, and the system is restarted only after maintenance personnel have inspected major components and found no abnormalities. Simultaneously, operational data is sent to R&D personnel for further root cause analysis. Of course, the parameter values ​​used in this plan are slightly different from those in the first-order modal frequency amplitude anomaly root cause diagnosis and maintenance plan. Specifically, the value of t2 remains consistent with t1, h can be 0.05g, i and k remain 0.05, and j ranges from 0.3 RPM to 0.4 RPM.

[0073] Reference Figure 5 The root cause diagnosis and maintenance plan for abnormal impeller modal frequency amplitude is as follows: First, using t2 as a data unit, continuously acquire the unit's rotational speed, ambient temperature, ambient humidity, and pitch angle under power generation conditions. Then, prepare the data, including performing spectrum calculation on the rotational speed, calculating the average values ​​of ambient temperature and humidity, and calculating the average air density based on the average ambient temperature and altitude. Next, determine whether the maximum value of the rotational speed spectrum amplitude is greater than m, and whether the frequency value corresponding to the maximum value of the rotational speed spectrum amplitude is within the frequency band of (1-n) to (1+n) times the actual impeller modal frequency. If so, it is determined that the impeller has experienced a modal frequency amplitude abnormality, and further determine whether the average ambient temperature is less than 0, the average ambient humidity is greater than p, and the pitch angle is less than the design minimum operating pitch angle + q. If yes, the cause of the anomaly is determined to be impeller icing, leading to blade stall and instability. The maintenance plan is to perform a fault protection shutdown until the ambient temperature rises above the target temperature, at which point the unit will automatically restart without requiring on-site inspection by maintenance personnel. If no, further determination is made as to whether both the average air density < r and the pitch angle < the design minimum operating pitch angle + q are simultaneously satisfied. If yes, the cause of the anomaly is determined to be low air density, leading to blade stall and instability. The maintenance plan is to perform a fault protection shutdown until the air density rises above the target density, at which point the unit will automatically restart without requiring on-site inspection by maintenance personnel. However, the operating data must be sent to the R&D personnel for adaptive adjustments to the control strategy after restarting. If no, the cause of the anomaly is determined to be blade damage or severe blade contamination, leading to blade stall and instability. The maintenance plan is to perform a fault shutdown, requiring on-site inspection by maintenance personnel to ensure the blades are normal before restarting, and the operating data must be sent to the R&D personnel for analysis. Among them, the value of t2 remains consistent with that of t1, the value of m ranges from 0.3 RPM to 0.4 RPM, n can be 0.05, o can be 2℃, p can be 0.7, q can be 0.5°, and r can be 1.1 g / L.

[0074] Reference Figure 6 The solution for identifying and maintaining abnormal frequency amplitudes in generating units beyond the scope of understanding involves first continuously acquiring the nacelle acceleration and rotational speed during unit operation, using t2 as a data unit, and then performing spectrum calculations. Next, it checks if the maximum amplitude of the nacelle acceleration spectrum is greater than s or the maximum amplitude of the rotational speed spectrum is greater than u. If so, it further checks whether it has triggered warnings or shutdowns for abnormal amplitudes of the first-order tower, second-order tower, and impeller in-plane modes. If triggered, it proceeds according to... Figures 3 to 5The process determines the cause of the anomaly and the maintenance plan. If it is not triggered, the cause of the anomaly is determined to be beyond the scope of understanding, and the maintenance plan is to shut down the system and restart it after maintenance personnel check that the major components are normal. At the same time, the operating data is sent to the R&D personnel for further analysis of the root cause. Among them, the value of t2 remains consistent with t1, s can be 0.05g, and the value of u ranges from 0.3RPM to 0.4RPM.

[0075] In general, this disclosure, through analysis, identifies numerous factors contributing to abnormal modal frequency amplitudes in wind turbine units. These factors primarily fall into three categories: control strategy design adaptability, structural damage to major components, and environmental factors. Environmental factors can be further subdivided into blade icing, severe blade surface contamination due to deposits, low air density caused by low ambient temperatures leading to blade stall and instability, and complex wind conditions (high turbulence). To address this, this disclosure, based on the operating principles of wind turbine units, provides a solution that integrates unit design, overall control adaptability, structural damage to major components, and environmental factors to diagnose the root causes of abnormal modal frequency amplitudes. Furthermore, it matches different levels of unit control protection and on-site operation and maintenance solutions based on varying diagnostic results to improve operational efficiency, reduce power generation losses, and enhance the economic benefits of wind farms.

[0076] Figure 7 This is a block diagram illustrating an anomaly diagnosis device for a wind turbine generator set according to an embodiment of the present disclosure.

[0077] Reference Figure 7 The abnormality diagnosis device 700 for wind turbine generator sets includes an acquisition unit 701, a determination unit 702, and a diagnosis unit 703.

[0078] The acquisition unit 701 can acquire the operating data of the wind turbine generator set within a first time period as reference operating data.

[0079] The determining unit 702 can determine the actual modal frequency of the target component of the wind turbine generator set based on reference operating data.

[0080] Optionally, the reference operating data includes at least one of the following: nacelle acceleration, speed, torque control data, and pitch rate control data; wherein, when the reference operating data includes nacelle acceleration, if the actual modal frequency of the target component includes the actual modal frequency within the impeller surface, then the nacelle acceleration includes lateral nacelle acceleration; if the actual modal frequency of the target component includes the actual modal frequency outside the impeller surface, then the nacelle acceleration includes aft and forward nacelle acceleration.

[0081] Optionally, the determining unit 702 may further: perform spectrum calculation on the reference operating data to obtain multiple reference frequency values ​​of the reference operating data and the amplitude corresponding to each of the multiple reference frequency values; determine the design frequency band of the target component based on the design modal frequency of the target component, wherein the design modal frequency of the target component is located within the design frequency band of the target component; select reference frequency values ​​that are within the design frequency band of the target component from the multiple reference frequency values ​​to obtain multiple candidate frequency values; and determine the candidate frequency value with the largest amplitude from the multiple candidate frequency values ​​as the actual modal frequency of the target component.

[0082] Optionally, the determining unit 702 may further: determine the actual modal frequencies of the target components in the multiple first time periods based on the reference operating data of the wind turbine generator set in the multiple first time periods; and determine the statistical values ​​of the actual modal frequencies of the target components in the multiple first time periods as the actual modal frequencies of the target components.

[0083] The acquisition unit 701 can also acquire the operating data of the wind turbine generator set during the second time period as diagnostic operating data.

[0084] The diagnostic unit 703 can determine the cause of the abnormality of the target component and the operation and maintenance plan based on the diagnostic operation data and the actual modal frequency of the target component.

[0085] Optionally, the acquisition unit 701 may also acquire the first operating data and rotational speed of the wind turbine generator set within a second time period, if the target component includes components other than the impeller, as diagnostic operating data; the diagnostic unit 703 may also: determine whether the target component has experienced abnormal modal frequency amplitude based on the first operating data and the actual modal frequency of the target component; if it is determined that the target component has experienced abnormal modal frequency amplitude, determine whether the target component has experienced resonance based on the rotational speed and the reference modal frequency, wherein the reference modal frequency is related to the actual modal frequency of the target component; and determine the cause of the abnormality of the target component and the operation and maintenance plan based on the determination result of whether the target component has experienced resonance.

[0086] Optionally, the diagnostic unit 703 can also determine that the target component is resonating if the maximum amplitude of the rotational speed is greater than the preset rotational speed amplitude, the frequency value corresponding to the maximum amplitude of the rotational speed, and the rotational speed harmonic are all close to the reference modal frequency. The rotational speed harmonic is calculated based on the rotational speed.

[0087] Optionally, the diagnostic unit 703 may also determine that the cause of the abnormality of the target component is a control strategy issue if the result indicates that the target component is resonating, and determine the operation and maintenance plan to output early warning information and adjust the control strategy.

[0088] Optionally, the actual modal frequencies of the target component include the actual first-order modal frequencies and the actual second-order modal frequencies of the target component. The diagnostic unit 703 may also: if it is determined that the target component has an abnormal first-order modal frequency amplitude and the determination result indicates that the target component has not resonated, determine that the cause of the abnormality of the target component is an occasional complex wind condition, and determine that the operation and maintenance plan is to output early warning information; if the number of occasional complex wind conditions exceeds the preset number within the third time period, determine that the cause of the abnormality of the target component is that the frequency of occasional complex wind conditions exceeds the limit, and determine that the operation and maintenance plan is to shut down and conduct on-site inspection; if it is determined that the target component has an abnormal second-order modal frequency amplitude and the determination result indicates that the target component has not resonated, determine that the cause of the abnormality of the target component is a component structural reason, and determine that the operation and maintenance plan is to shut down and conduct on-site inspection.

[0089] Optionally, if the target component includes the impeller, the acquisition unit 701 can also acquire the second operating data, environmental data, and pitch angle of the wind turbine generator set within a second time period as diagnostic operating data; the diagnostic unit 703 can also: determine whether the impeller has experienced a modal frequency amplitude abnormality based on the second operating data and the actual modal frequency of the impeller; if it is determined that the impeller has experienced a modal frequency amplitude abnormality, determine the cause of the impeller abnormality and the operation and maintenance plan based on the environmental data and the pitch angle.

[0090] Optionally, the environmental data includes ambient temperature, ambient humidity, and air density. The diagnostic unit 703 can also: if the ambient temperature is lower than the preset temperature, the ambient humidity is higher than the preset humidity, and the pitch angle is lower than the preset pitch angle, determine that the cause of the impeller abnormality is impeller icing, and determine the operation and maintenance plan is to shut down the machine until the ambient temperature is higher than the target temperature; if the air density is lower than the preset density and the pitch angle is lower than the preset pitch angle, determine that the cause of the impeller abnormality is low air density, and determine the operation and maintenance plan is to shut down the machine until the air density is higher than the target density, and adjust the control strategy after startup; if the cause of the impeller abnormality is not impeller icing or low air density, determine that the cause of the impeller abnormality is blade damage or severe blade contamination, and determine the operation and maintenance plan is to shut down the machine and conduct on-site inspection.

[0091] Optionally, the diagnostic unit 703 may also determine that the cause of the abnormality of the target component is beyond the scope of cognition, and determine the maintenance plan as shutdown and on-site inspection, when the maximum amplitude of the diagnostic operation data is greater than the preset amplitude and the cause of the abnormality of the modal frequency amplitude is not determined.

[0092] Regarding the apparatus in the above embodiments, the specific manner in which each unit performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0093] The anomaly diagnosis method for wind turbine generator sets according to embodiments of this disclosure can be programmed into a computer program and stored on a computer-readable storage medium. When the instructions corresponding to the computer program are executed by a processor, the anomaly diagnosis method for wind turbine generator sets as described above can be implemented. Examples of computer-readable storage media include: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disc storage, hard disk drive (HDD), solid-state drive (SSD), card storage (such as multimedia cards, secure digital (SD) cards, or ultra-fast digital (XD) cards), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, and any other device configured to store a computer program and any associated data, data files, and data structures in a non-transitory manner and to provide the computer program and any associated data, data files, and data structures to a processor or computer so that the processor or computer can execute the computer program. In one example, the computer program and any associated data, data files, and data structures are distributed across a networked computer system, such that the computer program and any associated data, data files, and data structures are stored, accessed, and executed in a distributed manner through one or more processors or computers.

[0094] Figure 8 This is a block diagram illustrating a computer device according to an embodiment of the present disclosure.

[0095] Reference Figure 8 The computer device 800 includes at least one memory 801 and at least one processor 802. The at least one memory 801 stores a set of computer-executable instructions. When the set of computer-executable instructions is executed by the at least one processor 802, an abnormality diagnosis method for a wind turbine generator set according to an exemplary embodiment of the present disclosure is performed.

[0096] As an example, computer device 800 may be a PC, tablet device, personal digital assistant, smartphone, or other device capable of executing the aforementioned set of instructions. Here, computer device 800 is not necessarily a single electronic device, but may be any collection of devices or circuits capable of executing the aforementioned instructions (or instruction sets) individually or in combination. Computer device 800 may also be part of an integrated control system or system manager, or may be configured to interconnect with a portable electronic device locally or remotely (e.g., via wireless transmission) through an interface.

[0097] In computer device 800, processor 802 may include 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, processor may also include analog processors, digital processors, microprocessors, multi-core processors, processor arrays, network processors, etc.

[0098] The processor 802 can execute instructions or code stored in the memory 801, which can also store data. Instructions and data can also be sent and received over a network via a network interface device, which can employ any known transmission protocol.

[0099] The memory 801 may be integrated with the processor 802, for example, by placing RAM or flash memory within an integrated circuit microprocessor. Alternatively, the memory 801 may include a separate device, such as an external disk drive, a storage array, or other storage device that can be used by any database system. The memory 801 and the processor 802 may be operatively coupled, or may communicate with each other, for example, via I / O ports, network connections, etc., enabling the processor 802 to read files stored in the memory.

[0100] In addition, the computer device 800 may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, mouse, touch input device, etc.). All components of the computer device 800 can be interconnected via a bus and / or network.

[0101] This disclosure provides a method, device, and storage medium for diagnosing anomalies in wind turbine generator sets. Considering that after the generator set is installed, the actual modal frequencies of each component often deviate from the design modal frequencies of the corresponding components, there is an inherent disadvantage of unreliable diagnostic benchmarks. By first determining reliable actual modal frequencies based on reference operating data, and then combining diagnostic operating data and actual modal frequencies for anomaly diagnosis, a clear cause of the anomaly and corresponding operation and maintenance plan can be determined, achieving more detailed anomaly diagnosis. Consequently, the generator is only shut down for inspection when necessary, thereby improving diagnostic efficiency and reducing losses caused by frequent shutdowns.

[0102] The specific embodiments of this disclosure have been described in detail above. Although some embodiments have been shown and described, those skilled in the art should understand that modifications and variations can be made to these embodiments without departing from the principles and spirit of this disclosure, which are defined by the claims and their equivalents. Such modifications and variations should also be within the protection scope of the claims of this disclosure.

Claims

1. A method for diagnosing anomalies in wind turbine generator sets, characterized in that, The abnormality diagnosis method includes: The operating data of the wind turbine generator set within a first time period is obtained as reference operating data; Based on the reference operating data, the actual modal frequencies of the target components of the wind turbine generator set are determined; The operating data of the wind turbine generator set during the second time period is obtained as diagnostic operating data. Based on the diagnostic operation data and the actual modal frequencies of the target component, determine the cause of the anomaly and the operation and maintenance plan for the target component; The step of determining the actual modal frequency of the target component of the wind turbine generator set based on the reference operating data includes: Perform spectrum calculations on the reference operating data to obtain multiple reference frequency values ​​of the reference operating data and the amplitude corresponding to each of the multiple reference frequency values; Based on the design modal frequencies of the target component, the design frequency band of the target component is determined, wherein the design modal frequencies of the target component are located within the design frequency band of the target component; From the plurality of reference frequency values, reference frequency values ​​that are within the design frequency band of the target component are selected to obtain a plurality of candidate frequency values; The candidate frequency value with the largest amplitude is determined from the plurality of candidate frequency values ​​and is taken as the actual modal frequency of the target component.

2. The abnormality diagnosing method according to claim 1, characterized by, Determining the actual modal frequency of the target component of the wind turbine generator set based on the reference operating data includes: Based on the reference operating data of the wind turbine generator set within multiple first durations, the actual modal frequencies of the target components within the multiple first durations are determined respectively. The statistical values ​​of the actual modal frequencies of the target component within each of the multiple first time periods are determined as the actual modal frequencies of the target component.

3. The abnormality diagnosis method as described in claim 1, characterized in that, The reference operating data includes at least one of the following: nacelle acceleration, speed, torque control data, and pitch rate control data; Wherein, if the reference operating data includes the nacelle acceleration, and the actual modal frequency of the target component includes the actual modal frequency within the impeller surface, then the nacelle acceleration includes the lateral nacelle acceleration; and if the actual modal frequency of the target component includes the actual modal frequency outside the impeller surface, then the nacelle acceleration includes the aft and forward nacelle accelerations.

4. The abnormality diagnosis method as described in claim 1, characterized in that, The acquisition of the wind turbine generator's operating data within a second time period, as diagnostic operating data, includes: If the target component includes components other than the rotor, the first operating data and rotational speed of the wind turbine generator set within the second time period are obtained as the diagnostic operating data. The step of determining the cause of the anomaly and the maintenance plan for the target component based on the diagnostic operation data and the actual modal frequency of the target component includes: Based on the first operating data and the actual modal frequency of the target component, determine whether the target component has experienced an abnormal modal frequency amplitude. If it is determined that the target component has an abnormal modal frequency amplitude, it is determined whether the target component has resonance based on the rotational speed and the reference modal frequency, wherein the reference modal frequency is related to the actual modal frequency of the target component; Based on the determination of whether the target component resonates, the cause of the abnormality of the target component and the operation and maintenance plan are determined.

5. The abnormality diagnosing method according to claim 4, characterized in that, The step of determining whether the target component resonates based on the rotational speed and the reference modal frequency includes: When the maximum amplitude of the rotational speed is greater than the preset rotational speed amplitude, the frequency value corresponding to the maximum amplitude of the rotational speed, and the rotational speed harmonic are all close to the reference mode frequency, it is determined that the target component resonates, wherein the rotational speed harmonic is calculated based on the rotational speed.

6. The abnormality diagnosing method according to claim 4, characterized in that, The step of determining the cause of the abnormality and the maintenance plan for the target component based on the determination result of whether the target component resonates includes: If the determination result indicates that the target component is resonating, the cause of the abnormality of the target component is determined to be due to the control strategy, and the operation and maintenance solution is to output early warning information and adjust the control strategy.

7. The abnormality diagnosis method as described in claim 4, characterized in that, The actual modal frequencies of the target component include the actual first-order modal frequencies and the actual second-order modal frequencies of the target component. The step of determining the cause of the anomaly and the maintenance plan for the target component based on the determination of whether resonance has occurred includes: If it is determined that the target component has an abnormal first-order modal frequency amplitude, and the determination result indicates that the target component has not resonated, the cause of the abnormality of the target component is determined to be an occasional complex wind condition, and the operation and maintenance plan is determined to output early warning information; If the number of times an occasional complex wind condition occurs exceeds a preset number within the third time period, the cause of the abnormality of the target component is determined to be that the frequency of occasional complex wind conditions exceeds the limit, and the operation and maintenance plan is determined to be shutdown and on-site inspection. If it is determined that the target component has an abnormal second-order modal frequency amplitude and the determination result indicates that the target component has not resonated, the cause of the abnormality of the target component is determined to be a component structure issue, and the operation and maintenance plan is determined to be shutdown and on-site inspection.

8. The abnormality diagnosis method as described in claim 1, characterized in that, The acquisition of the wind turbine generator's operating data within a second time period, as diagnostic operating data, includes: When the target component includes an impeller, the second operating data, environmental data, and pitch angle of the wind turbine generator set within the second time period are acquired as the diagnostic operating data. The step of determining the cause of the impeller's abnormality and the operation and maintenance plan based on the diagnostic operation data and the actual modal frequency of the impeller includes: Based on the second operating data and the actual modal frequency of the impeller, determine whether the impeller has experienced abnormal modal frequency amplitude. If it is determined that the impeller has an abnormal modal frequency amplitude, the cause of the impeller abnormality and the operation and maintenance plan shall be determined based on the environmental data and the pitch angle.

9. The abnormality diagnosing method according to claim 8, characterized in that, The environmental data includes ambient temperature, ambient humidity, and air density. The step of determining the cause of the impeller malfunction and the maintenance plan based on the environmental data and the blade pitch angle includes: If the ambient temperature is less than the preset temperature, the ambient humidity is greater than the preset humidity, and the pitch angle is less than the preset pitch angle, the cause of the impeller abnormality is determined to be impeller icing, and the operation and maintenance plan is to shut down the machine until the ambient temperature is greater than the target temperature. If both the air density and the blade pitch angle are less than the preset density, the cause of the impeller abnormality is determined to be low air density, and the operation and maintenance plan is to shut down the machine until the air density is greater than the target density, and adjust the control strategy after startup. If the cause of the impeller malfunction is not impeller icing or low air density, determine that the cause of the impeller malfunction is blade damage or severe blade contamination, and determine the operation and maintenance plan as shutdown and on-site inspection.

10. The abnormality diagnosing method according to any one of claims 4 to 9, characterized by, The step of determining the cause of the anomaly and the maintenance plan for the target component based on the diagnostic operation data and the actual modal frequency of the target component further includes: If the maximum amplitude of the diagnostic operation data is greater than the preset amplitude, and the cause of the abnormal modal frequency amplitude and the operation and maintenance plan are not determined, the cause of the abnormality of the target component is determined to be beyond the scope of cognition, and the operation and maintenance plan is determined to be shutdown and on-site inspection.

11. An anomaly diagnosis device for a wind turbine generator set, characterized in that, The abnormality diagnostic device includes: The acquisition unit is configured to acquire the operating data of the wind turbine generator set within a first time period as reference operating data. The determining unit is configured to determine the actual modal frequency of the target component of the wind turbine generator set based on the reference operating data; The acquisition unit is also configured to acquire the operating data of the wind turbine generator set during a second time period as diagnostic operating data. The diagnostic unit is configured to determine the cause of the abnormality of the target component and the operation and maintenance plan based on the diagnostic operation data and the actual modal frequency of the target component. The determining unit is further configured to: perform spectrum calculation on the reference operating data to obtain multiple reference frequency values ​​of the reference operating data and the amplitude corresponding to each of the multiple reference frequency values; determine the design frequency band of the target component based on the design modal frequency of the target component, wherein the design modal frequency of the target component is located within the design frequency band of the target component; filter out reference frequency values ​​that are within the design frequency band of the target component from the multiple reference frequency values ​​to obtain multiple candidate frequency values; and determine the candidate frequency value with the largest amplitude from the multiple candidate frequency values ​​as the actual modal frequency of the target component.

12. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by at least one processor, the at least one processor causes the at least one processor to perform the abnormal diagnosis method for a wind turbine generator as described in any one of claims 1 to 10.

13. A computer device, comprising: include: At least one processor; At least one memory that stores computer-executable instructions. Wherein, when the computer-executable instructions are executed by the at least one processor, the at least one processor causes the at least one processor to execute the abnormal diagnosis method for the wind turbine generator set as described in any one of claims 1 to 10.

Images