Clearance abnormality detection method and apparatus for wind turbine generator set

Abstract

A clearance abnormality detection method for a wind turbine generator set. The method comprises: acquiring, from operation data of a generator set within a predetermined period of time, operation data of when an air speed is within a predetermined air speed range and a power is within a predetermined power range, and dividing the operation data into a plurality of operation data fragments; with regard to each operation data fragment, when a first specified clearance value therein is less than a first preset value and the operation data fragment meets a preset condition, determining the operation data fragment to be a clearance-abnormal fragment; and determining a clearance abnormality of the generator set according to the clearance-abnormal fragment. Further comprised are a clearance abnormality detection apparatus for a wind turbine generator set, and a medium, a system and a wind turbine generator set. The method can effectively solve the problem of it being impossible to predict a clearance risk of a wind turbine generator set in advance.

Description

Wind turbine clearance anomaly detection method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure claims priority to the Chinese patent application filed with the China Patent Office on December 30, 2022, with application number 202211734407.8 and invention name "Method and device for detecting clearance anomalies of wind turbine generator sets", the entire contents of which are incorporated by reference into this application. Technical Field

[0003] The present disclosure generally relates to the field of wind power generation technology, and more specifically, to a method and apparatus for detecting abnormal clearance of a wind turbine generator set. Background Art

[0004] While lightweight blade design is an effective measure to reduce blade costs, the resulting reduction in stiffness can result in substandard clearance, increasing the risk of blade sweeps. Furthermore, complex wind conditions in some wind farms make it difficult to determine blade operating conditions, leading to frequent tower sweeps in in-service models and a high number of wind turbines at risk. Due to these safety risks, some wind turbines, particularly those with large rotors or located in complex terrain, have installed tower clearance monitoring equipment to ensure proper operation and prevent blade sweeps.

[0005] At present, wind turbines mainly detect clearance anomalies based on the clearance values ​​monitored in real time by clearance monitoring equipment, which is mainly used for control and safety protection of wind turbines. This solution focuses on real-time detection of wind turbines and cannot predict the clearance risks of wind turbines in advance.

[0006] Summary of the Invention

[0007] The embodiments of the present disclosure provide a method and device for detecting clearance anomalies of a wind turbine generator set, which can effectively solve the problem that the prior art cannot predict the clearance risk of a wind turbine generator set in advance.

[0008] In one aspect, a method for detecting clearance anomalies of a wind turbine generator set is provided, comprising: obtaining operating data of the wind turbine generator set within a predetermined time; obtaining first operating data from the operating data, in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range; dividing the first operating data into multiple operating data segments; for each operating data segment, if a first specified clearance value in the operating data segment is less than a first preset value and the operating data segment meets a preset condition, determining the operating data segment as a clearance anomaly segment, wherein the preset condition is associated with the number of operating data in the operating data segment whose clearance value is less than the first preset value; and determining the clearance anomaly of the wind turbine generator set based on the clearance anomaly segment.

[0009] In another general aspect, a clearance anomaly detection device for a wind turbine generator set is provided, comprising: a first acquisition unit configured to acquire operating data of the wind turbine generator set within a predetermined time; a second acquisition unit configured to acquire first operating data in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range from the operating data; a grouping unit configured to divide the first operating data into operating data segments; a first determination unit configured to, for each operating data segment, determine the operating data segment as a clearance anomaly segment if a first specified clearance value in the operating data segment is less than a first preset value and the operating data segment meets a preset condition, wherein the preset condition is associated with the number of operating data in which the clearance value in the operating data segment is less than the first preset value; and a second determination unit configured to determine the clearance anomaly of the wind turbine generator set based on the clearance anomaly segment.

[0010] In another aspect, a computer-readable storage medium storing instructions is provided, wherein when the instructions are executed by at least one computing device, the at least one computing device is prompted to perform any of the above-mentioned methods for detecting clearance anomalies of a wind turbine generator set.

[0011] In another aspect, a system comprising at least one computing device and at least one storage device storing instructions is provided, wherein the instructions, when executed by the at least one computing device, prompt the at least one computing device to execute any of the above-mentioned wind turbine clearance anomaly detection methods.

[0012] In another aspect, a wind turbine generator set is provided, comprising the above-mentioned clearance anomaly detection device for the wind turbine generator set.

[0013] According to the wind turbine clearance anomaly detection method and device of the embodiment of the present disclosure, the qualified operating data are grouped, and the clearance anomaly segments are determined based on the clearance values ​​in the grouped operating data segments through correlation analysis. Then, based on the clearance anomaly segments, it is determined whether the clearance of the wind turbine is abnormal. This allows the clearance risk of the wind turbine to be predicted in advance when the clearance is abnormal, without having to wait until the clearance risk exists to know. Therefore, when the clearance of the wind turbine is abnormal, the wind turbine can be adjusted in time to avoid the occurrence of a tower sweeping incident. Therefore, the present disclosure can effectively solve the problem that the existing technology cannot predict the clearance risk of the wind turbine in advance.

[0014] Additional aspects and / or advantages of the present general inventive concept will be set forth in part in the following description and in part will be apparent from the description, or may be learned through practice of the present general inventive concept. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other objects and features of the embodiments of the present disclosure will become more apparent through the following description in conjunction with the accompanying drawings showing the embodiments, in which:

[0016] FIG1 is a flow chart illustrating a method for detecting abnormal clearance of a wind turbine generator system according to one or more embodiments of the present disclosure;

[0017] FIG2 is a timing diagram showing ten minutes before and after a clearance anomaly segment according to one or more embodiments of the present disclosure;

[0018] FIG3 is a complete flow chart illustrating clearance anomaly detection according to one or more embodiments of the present disclosure;

[0019] FIG4 is a diagram showing a headroom minimum value curve, a headroom maximum value curve, or a headroom average value curve corresponding to different power bins according to one or more embodiments of the present disclosure;

[0020] FIG5 is a diagram showing a minimum clearance curve, a maximum clearance curve, or an average clearance curve corresponding to different pitch angle bins according to one or more embodiments of the present disclosure;

[0021] FIG6 is a schematic diagram illustrating a minimum clearance curve according to one or more embodiments of the present disclosure;

[0022] FIG7 is a schematic diagram showing the position of a wind turbine generator system according to one or more embodiments of the present disclosure;

[0023] FIG8 is a schematic diagram showing K-proximity distance of a wind turbine generator system according to one or more embodiments of the present disclosure;

[0024] FIG9 is a schematic diagram showing the local achievable density of a wind turbine generator system according to one or more embodiments of the present disclosure;

[0025] FIG10 is a schematic diagram of a wind turbine generator system used for local abnormal factors according to one or more embodiments of the present disclosure;

[0026] FIG11 is a schematic diagram showing the results of local anomaly factors according to one or more embodiments of the present disclosure;

[0027] FIG12 is a line diagram illustrating local anomaly factor results according to one or more embodiments of the present disclosure;

[0028] FIG13 is a complete flow chart illustrating outlier identification according to one or more embodiments of the present disclosure;

[0029] FIG14 is a block diagram illustrating a clearance anomaly detection apparatus for a wind turbine generator system according to one or more embodiments of the present disclosure. DETAILED DESCRIPTION

[0030] The following detailed description is provided to help the reader gain a comprehensive understanding of the methods, devices and / or systems described herein. However, various changes, modifications and equivalents of the methods, devices and / or systems described herein will be clear after understanding the disclosure of the present application. For example, the order of operations described herein is merely an example and is not limited to those orders set forth herein, but can be changed as will be clear after understanding the disclosure of the present application, except for operations that must occur in a specific order. In addition, for greater clarity and conciseness, descriptions of features known in the art may be omitted.

[0031] The features described herein can be implemented in different forms and should not be construed as limited to the examples described herein. Rather, the examples described herein are provided to illustrate only some of the many possible ways to implement the methods, devices, and / or systems described herein, which will become clear after understanding the disclosure of this application.

[0032] As used herein, the term "and / or" includes any one of the associated listed items and any combination of any two or more.

[0033] Although terms such as "first," "second," and "third" may be used herein to describe various members, components, regions, layers, or portions, these members, components, regions, layers, or portions should not be limited by these terms. Instead, these terms are used solely to distinguish one member, component, region, layer, or portion from another member, component, region, layer, or portion. Thus, what is referred to as a first member, first component, first region, first layer, or first portion in the examples described herein may also be referred to as a second member, second component, second region, second layer, or second portion without departing from the teachings of the examples.

[0034] In the specification, when an element (such as a layer, region, or substrate) is described as being “on,” “connected to,” or “coupled to” another element, the element may be directly “on,” “connected to,” or “coupled to” the other element, or one or more other elements may be present therebetween. Conversely, when an element is described as being “directly on,” “directly connected to,” or “directly coupled to” another element, there may be no other elements present therebetween.

[0035] The terms used herein are only used to describe various examples and are not intended to limit the disclosure. Unless the context clearly indicates otherwise, the singular is intended to include the plural. The terms "comprise," "include," and "have" indicate the presence of the recited 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.

[0036] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure pertains after understanding the present disclosure. Unless expressly defined otherwise herein, terms (such as those defined in general dictionaries) should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and should not be interpreted in an idealized or overly formal manner.

[0037] Furthermore, in describing the examples, when it is deemed that a detailed description of well-known related structures or functions would cause ambiguous interpretation of the present disclosure, such detailed description will be omitted.

[0038] The present disclosure provides a method and device for detecting clearance anomalies of a wind turbine generator set, which can predict the clearance risk of a wind turbine generator set in advance. The method of predicting the clearance risk of a wind turbine generator set in advance can be applied to a server, a controller of a single wind turbine, or a master controller of a wind farm. The present disclosure does not limit this. The server, the controller, and the wind turbine generator set can be connected wirelessly or by wire, which is not limited here. The above-mentioned server can be a single server, a server cluster composed of several servers, or a cloud computing platform or a virtualization center. The following is an explanation using a server as an example.

[0039] The server obtains the operating data of the wind turbine generator set within a predetermined time; obtains first operating data from the operating data, in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range; divides the first operating data into multiple operating data segments, and for each operating data segment, when a first specified clearance value in the operating data segment is less than a first preset value and the operating data segment meets a preset condition, determines the operating data segment as a clearance abnormality segment, wherein the preset condition is associated with the number of operating data in the operating data segment whose clearance value is less than the first preset value; determines the clearance abnormality of the wind turbine generator set according to the clearance abnormality segment, so that the clearance risk of the wind turbine generator set can be predicted in advance when the clearance abnormality occurs, without having to wait until the clearance risk exists to know it, so that when the wind turbine generator set has a clearance abnormality, the wind turbine generator set can be adjusted in time to avoid a tower sweeping incident.

[0040] The wind turbine clearance anomaly detection method and device disclosed herein are described in detail below with reference to the accompanying drawings.

[0041] The present disclosure proposes a method for detecting clearance anomalies of a wind turbine generator set. FIG1 is a flow chart illustrating the method for detecting clearance anomalies of a wind turbine generator set according to one or more embodiments of the present disclosure. Referring to FIG1 , the method for detecting clearance anomalies of a wind turbine generator set includes the following steps:

[0042] In step S101, operating data of the wind turbine generator set within a predetermined time period is obtained. The predetermined time period in this step can be set as needed and is not limited in this disclosure. The operating data in this step can include variables such as the wind turbine generator set's grid-side active power, blade pitch angle, headroom value, wind speed, and other variables. Other data can also be included and can be set as needed and is also not limited in this disclosure. The power mentioned later in this disclosure refers to the grid-side active power.

[0043] In step S102, first operating data is obtained from the operating data, in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range. The predetermined wind speed range and the predetermined power range in this step may be near the rated wind speed and the rated power. For example, the predetermined wind speed range may be the interval of rated wind speed*80% to rated wind speed*110% (such as the interval of 8 to 13 m / s), and the predetermined power range may be the interval of rated power*80% to rated power*110%. Of course, the predetermined wind speed range and the predetermined power range may also be data of other wind speed segments and other power segments. It should be noted that if the predetermined wind speed range is near the rated wind speed, the predetermined power range also needs to be selected near the rated power; if the predetermined wind speed range selects other wind speed segments, the predetermined power range also needs to be selected from other power segments.

[0044] According to an embodiment of the present disclosure, before obtaining first operating data from the operating data indicating that the wind speed is within a predetermined wind speed range and the power is within a predetermined power range, the clearance anomaly detection method may further include the following steps: performing power binning on the operating data to divide the operating data into multiple power intervals and obtaining a second specified clearance value for the operating data within each power interval; in response to the ratio of the number of power intervals within the first predetermined range to the total number of power intervals within the predetermined power range for the second specified clearance value within the predetermined power range reaching a second predetermined ratio, determining that the first clearance detection device flag indicates that there is no abnormality in the calibration of the clearance detection device. According to this embodiment, by performing correlation analysis between the clearance value and variables such as power, it is possible to conveniently and accurately determine whether the calibration of the clearance detection device is abnormal.

[0045] Specifically, if the predetermined wind speed range and the predetermined power range are near the rated wind speed and rated power, then the second designated clearance value may be the maximum clearance value, or other designated clearance values, which are not limited in this disclosure. The first predetermined range may be 8 to 12 meters, or other ranges, which are not limited in this disclosure. The second predetermined ratio may be 80%, or other ratios, which are also not limited in this disclosure. For example, taking the second designated clearance value as the maximum clearance value, the first predetermined range being 8 to 12 meters, and the second predetermined ratio being 80% as an example, the grid-side power of all operating data can be counted, and the operating data can be binned with 200KW grid-side power as a power interval to obtain multiple power intervals. Then, within the range of rated power * 80% to rated power * 110% (i.e., the predetermined power range), if the maximum clearance values ​​in 80% of the power intervals are all between 8 and 12 meters, then the first clearance detection device flag is output as 1; otherwise, the first clearance detection device flag is output as 0.

[0046] According to an embodiment of the present disclosure, before obtaining first operating data in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range from the operating data, the clearance abnormality detection method may further include the following steps: performing angle binning on the operating data to divide the operating data into multiple pitch angle intervals, and obtaining a second specified clearance value of the operating data in each pitch angle interval; in response to the ratio of the number of pitch angle intervals within the first predetermined range with the second specified clearance value to the total number of pitch angle intervals within the range from the minimum pitch angle to the predetermined degree reaching a second predetermined ratio, determining that the second clearance detection device flag indicates that there is no abnormality in the calibration of the clearance detection device. According to this embodiment, by performing correlation analysis between the clearance value and variables such as the pitch angle, it is also possible to conveniently and accurately determine whether the calibration of the clearance detection device is abnormal.

[0047] Specifically, if the predetermined wind speed range and the predetermined power range are near the rated wind speed and rated power, then the second designated clearance value may be the maximum clearance value, or other designated clearance values, which are not limited in this disclosure. The first predetermined range may be 8 to 12 meters, or other ranges, which are not limited in this disclosure. The second predetermined ratio may be 80%, or other ratios, which are also not limited in this disclosure. The predetermined degree may be set as needed, but is generally greater than the binning angle. For example, taking the second designated clearance value as the maximum clearance value, the first predetermined range being 8 to 12 meters, the second predetermined ratio being 80%, and the predetermined angle being 5 degrees as an example, the pitch angles of all operating data may be counted, and the operating data may be binned into pitch angle intervals of 1 degree pitch angle, resulting in multiple pitch angle intervals. Then, within the range from the minimum pitch angle to 5 degrees, if the maximum clearance values ​​in 80% of the power intervals are all between 8 and 12 meters, then a second clearance detection device flag is output as 1; otherwise, the second clearance detection device flag is output as 0.

[0048] According to an embodiment of the present disclosure, in response to both the first clearance detection device flag and the second clearance detection device flag indicating that the clearance detection device calibration is normal, it is determined that the clearance detection device calibration is normal. According to this embodiment, the clearance detection device is determined to be normal only when both the first clearance detection device flag and the second clearance detection device flag indicate that the clearance detection device calibration is normal, which can more accurately determine the calibration status of the clearance detection device.

[0049] Specifically, only when the first clearance detection device flag and the second clearance detection device flag both indicate that there is no abnormality in the clearance detection device calibration can it be determined that there is no abnormality in the clearance detection device, that is, it is determined that the obtained operating data is valid. Only then can the first operating data showing that the wind speed is within the predetermined wind speed range and the power is within the predetermined power range be obtained from the valid operating data.

[0050] According to an embodiment of the present disclosure, the clearance anomaly detection method may further include the following steps: in response to a clearance detection device calibration anomaly, obtaining a first specified clearance value of the operating data within each power interval; in response to the ratio of the number of power intervals within the second predetermined range of the first specified clearance value to the total number of power intervals within the predetermined power range reaching a third predetermined ratio within the predetermined power range, determining that the first clearance value flag indicates that the clearance value is normal; otherwise, determining that the wind turbine generator set is predicted to have a low clearance risk and issuing a prompt message to immediately calibrate the clearance detection device. According to this embodiment, in the case of a clearance detection device calibration anomaly, further correlation analysis can be performed between the clearance value and variables such as power to determine whether the clearance value at this time is obviously abnormal. If it is obviously abnormal, the clearance detection device can be immediately calibrated so that an accurate clearance value can be obtained as soon as possible and clearance anomaly detection can be performed in a timely manner.

[0051] Specifically, if the predetermined wind speed range and the predetermined power range are near the rated wind speed and rated power, the first designated clearance value may be the minimum clearance value, or other designated clearance values, which are not limited in this disclosure. The second predetermined range may be 5-8 meters, or other ranges, which are not limited in this disclosure. The third predetermined ratio may be 80%, or other ratios, which are also not limited in this disclosure. For example, taking the first designated clearance value as the minimum clearance value, the second predetermined range as 5-8 meters, and the third predetermined ratio as 80% as an example, the grid-side power of all operating data can be counted, and the operating data can be binned with 200KW grid-side power as a power interval to obtain multiple power intervals. Then, within the range of rated power * 80% to rated power * 110% (i.e., the predetermined power range), if the minimum clearance values ​​in 80% of the power intervals are all between 5 and 8 meters, then the first clearance value flag bit is output as 1; otherwise, the first clearance value flag bit is output as 0.

[0052] According to an embodiment of the present disclosure, the clearance anomaly detection method may further include the following steps: in response to a clearance detection device calibration anomaly, obtaining a first specified clearance value of the operating data within each pitch angle interval; in response to the ratio of the number of pitch angle intervals within the second predetermined range of the first specified clearance value to the total number of pitch angle intervals within the range of the minimum pitch angle to the predetermined degree reaching a third predetermined ratio, determining that the second clearance value flag indicates that the clearance value is normal; otherwise, determining that the wind turbine generator set is predicted to have a low clearance risk and issuing a prompt message to immediately calibrate the clearance detection device. According to this embodiment, in the case of a clearance detection device calibration anomaly, it is possible to further determine whether the clearance value is obviously abnormal by analyzing the correlation between the clearance value and variables such as the pitch angle. If it is obviously abnormal, it may be necessary to immediately calibrate the clearance detection device so that an accurate clearance value can be obtained and clearance anomaly detection can be performed in a timely manner.

[0053] Specifically, if the predetermined wind speed range and the predetermined power range are near the rated wind speed and rated power, the first designated clearance value may be the minimum clearance value, or other designated clearance values, which are not limited in this disclosure. The second predetermined range may be 5-8 meters, or other ranges, which are not limited in this disclosure. The third predetermined ratio may be 80%, or other ratios, which are also not limited in this disclosure. The predetermined degree may be set as needed, but is generally greater than the binning angle. For example, taking the first designated clearance value as the minimum clearance value, the second predetermined range as 5-8 meters, the third predetermined ratio as 80%, and the predetermined angle as 5 degrees as an example, the pitch angles of all operating data can be counted, and the operating data can be binned into pitch angle intervals of 1 degree pitch angle to obtain multiple pitch angle intervals. Then, within the minimum pitch angle to 5 degrees range, if the minimum clearance values ​​in 80% of the power intervals are all between 5 and 8 meters, a first clearance value flag bit is output as 1; otherwise, a first clearance value flag bit is output as 0.

[0054] According to an embodiment of the present disclosure, the clearance anomaly detection method may further include the following steps: in response to both the first clearance value flag and the second clearance value flag indicating that the clearance value is normal, determining that the clearance value is normal; otherwise, determining that the wind turbine is predicted to have a low clearance risk and issuing a prompt message to immediately calibrate the clearance detection device. According to this embodiment, the clearance value is determined to be normal only when both the first clearance value flag and the second clearance value flag indicate that the clearance value is normal. That is, as long as one of the clearance value flags indicates that the clearance value is abnormal, the clearance detection device is immediately calibrated to ensure that the clearance calibration device can be recalibrated in a timely manner.

[0055] Specifically, only when both the first clearance value flag and the second clearance value flag indicate that the clearance value is normal, it is determined that the clearance value is normal. Only at this time, there is no need to immediately calibrate the clearance detection device. That is, once any clearance value flag indicates that the clearance value is abnormal, it is necessary to send a prompt message to immediately calibrate the clearance detection device to ensure that the clearance calibration device can be recalibrated in time.

[0056] According to an embodiment of the present disclosure, obtaining first operating data from operating data, in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range, may include: obtaining second operating data from the operating data, in which the clearance value is within a third predetermined range; obtaining the sum of the durations of each operating data in the second operating data as the first duration; obtaining the duration between the start time and the end time of the operating data as the second duration; and in response to the first duration and the second duration satisfying the integrity condition, obtaining first operating data from the operating data, in which the wind speed is within the predetermined wind speed range and the power is within the predetermined power range. According to this embodiment, it can be ensured that the operating data collected within the predetermined time is sufficient, avoiding the situation where too little operating data is collected, resulting in the first operating data obtained not being well used for subsequent clearance analysis.

[0057] Specifically, the integrity condition may be that the ratio of the first duration to the second duration is greater than a first preset threshold. The first preset threshold can be set as needed and is not limited by this disclosure. The third predetermined range may be an open set (0, 100), that is, when the headroom value is within (0, 100), it indicates that the corresponding operating data has a headroom value. Of course, in different scenarios, the third predetermined range can be set as needed and is not limited by this disclosure. It should be noted that after obtaining the operating data, it is also necessary to determine whether the wind turbine generator set is installed with a clearance detection device or whether the clearance detection device is turned on, so as to pre-determine whether the obtained operating data is valid. The specific judgment method can be as follows: identify the clearance value corresponding to each piece of operating data obtained. If the clearance values ​​of all operating data are 100 (different values ​​are set according to different wind turbine generator sets), it means that the wind turbine generator set is not installed with a clearance detection device or the clearance detection device is not turned on or the clearance detection device is not operating. At this time, "the clearance detection device is not installed or not turned on" can be output. Of course, the output content can be saved, such as in the form of a data table; if the clearance values ​​of all operating data have a value within the range of 0 to 100, it means that the clearance detection device has been installed and turned on normally. At this time, "the clearance detection device is installed and turned on normally" can be output. Of course, the output content can also be saved, such as in the form of a data table.

[0058] For example, taking the integrity condition that the ratio of the first duration to the second duration is greater than the first preset threshold and the third preset range is the open set (0, 100) as an example, first, the second operating data with a clearance value within the open set (0, 100) is obtained from the operating data; secondly, the duration of each second operating data is obtained. If, when obtaining the duration of each second operating data, it is found that the duration of a certain second operating data exceeds more than twice the average of the durations of all second operating data, the duration of the second operating data is redefined as the average of the durations of all second operating data. It should be noted that twice the above average can be set to other values ​​as needed, and the present disclosure is not limited thereto; furthermore, the sum of the durations of all second operating data is obtained as t1, and at the same time, the duration between the start time and the end time of all operating data is obtained as t2; finally, t1 / t2 is calculated. When the ratio is greater than the first preset threshold, it is determined that the operating data is complete and subsequent clearance analysis can be performed; at this time, the integrity information of each wind turbine generator set can be output to the data table, that is, saved and displayed.

[0059] According to an embodiment of the present disclosure, obtaining first operating data from operating data, in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range, may include: obtaining third operating data from the operating data, in a grid-connected state, with a headroom value greater than a fourth preset value and less than a fifth preset value; taking the sum of the durations of each operating data item in the third operating data as the third duration; obtaining the duration between the start time and the end time of the operating data as the second duration, wherein the second operating data is operating data in which the headroom value in the operating data is within the third predetermined range; and in response to the third duration and the second duration satisfying a validity condition, obtaining first operating data from the operating data, in which the wind speed is within the predetermined wind speed range and the power is within the predetermined power range. According to this embodiment, the operating data collected within the predetermined time can be ensured to be valid, avoiding the headroom value in the collected operating data being too small or too large, resulting in the first operating data being unable to be well used for subsequent headroom analysis.

[0060] Specifically, the fourth preset value and the fifth preset value can be set as needed. For example, the fourth preset value can be set to 0, and the fifth preset value can be set to 20. This disclosure does not limit this. The validity condition can be that the ratio of the third duration to the second duration is greater than a second preset threshold. The second preset threshold can be set as needed and is not limited by this disclosure.

[0061] For example, taking the validity condition that the ratio of the third duration to the second duration is greater than the second preset threshold, the fourth preset value can be set to 0, and the fifth preset value can be set to 20 as an example, first, from the operating data, the third operating data with a clearance value greater than 0 and less than 20 in the grid-connected state is screened; secondly, each third operating data is obtained and the duration of each of the above data is calculated. If, when obtaining the duration of each second operating data, it is found that the duration of a second operating data exceeds more than twice the average of the durations of all second operating data, the duration of the second operating data is redefined as the average of the durations of all second operating data. It should be noted that twice the above average can be set to other values ​​as needed, and the present disclosure is not limited thereto; furthermore, the sum of the durations of all third operating data is obtained as t3; at the same time, the duration between the start time and the end time of all operating data is obtained as t2; finally, t3 / t2 is calculated. When the ratio is greater than the second preset threshold, it is determined that the obtained operating data is valid and subsequent clearance analysis can be performed. At this time, the integrity information of each wind turbine generator set can be output to the data table, that is, saved and displayed.

[0062] In step S103, the first operating data is divided into a plurality of operating data segments. The sampling time of the operating data in each operating data segment in this step is continuous, although this disclosure is not limited to this. For example, each piece of operating data acquired within a predetermined time period of the wind turbine generator set's operating data corresponds to its own index value, and the operating data can be divided based on whether the index values ​​are continuous, i.e., the index values ​​in each segmented operating data segment are continuous.

[0063] According to an embodiment of the present disclosure, for each operational data segment, the duration between the start time and the end time of the operational data segment is obtained as the duration of the operational data segment; if the sum of the durations of a predetermined number of consecutive operational data segments is less than the predetermined duration, the predetermined number of operational data segments are merged, and the merged operational data segments are used to replace the predetermined number of operational data segments. According to this embodiment, when a single operational data segment is short, multiple operational data segments can be merged to reduce the workload of processing the operational data segments.

[0064] Specifically, after dividing into multiple operation data segments, the start time and end time of each operation data segment can be obtained. The time between the start time and the end time is the duration of the operation data segment. It should be noted that a certain operation data segment after division may only include one operation data. In this case, the operation data segment generally does not exceed 60 seconds. Therefore, when the operation data segments before and / or after the operation data segment do not exceed 60 seconds, it can be considered to merge the operation data segment with the operation data segments before and / or after it to reduce the number of operation data segments. It should be noted that the above 60 seconds can also be 50 seconds or 70 seconds. The specific setting can be based on needs and is not limited by this disclosure.

[0065] In step S104, for each operating data segment, if the first specified clearance value in the operating data segment is less than the first preset value and the operating data segment meets the preset condition, the operating data segment is determined to be a clearance abnormality segment, wherein the preset condition is associated with the number of operating data in the operating data segment whose clearance value is less than the first preset value. The first specified clearance value in this step can be the minimum clearance value, or other specified clearance values, and the present disclosure is not limited to this. For the first preset value in this step, when the predetermined wind speed range and the predetermined power range correspond to the rated wind speed and rated power, 5m can be considered as the first preset value. Of course, other values ​​can also be selected, and the present disclosure is not limited to this. The preset condition of this step can be that the number of operating data in the operating data segment whose clearance value is less than the first preset value reaches a certain number. This number can be set according to user needs, or can be determined based on the total number of operating data in the operating data segment, and the present disclosure is not limited to this.

[0066] For example, taking the first preset value as 5m and the first designated clearance value as the minimum clearance value as an example, for each operating data segment, if the minimum clearance value in the operating data segment is greater than or equal to 5m, then the operating data segment has no abnormality; if the minimum clearance value in the operating data segment is less than 5m and the operating data segment meets the preset conditions, then the operating data segment is a clearance abnormality segment; if the minimum clearance value in the operating data segment is less than 5m and the operating data segment does not meet the preset conditions, then the operating data segment has no abnormality.

[0067] According to an embodiment of the present disclosure, the preset condition may include one of the following: the number of operating data items within an operating data segment whose clearance value is less than a first preset value is greater than a second preset value; or the ratio of the number of operating data items within an operating data segment whose clearance value is less than the first preset value to the total number of operating data items within the operating data segment reaches a first predetermined ratio. With this embodiment, the preset condition can be determined by setting the second preset value as needed, or by determining the preset condition based on the total number of operating data items within each operating data segment. This allows the preset condition to be flexibly set while accurately identifying abnormal clearance segments.

[0068] Specifically, the second preset value can be set as needed, for example, it can be set to 10, it can be set to 9, or it can be set to 11, and this disclosure does not limit this. The first predetermined ratio can also be set as needed, for example, it can be 50%, it can be 45%, or it can be set to 55%, and this disclosure does not limit this. For example, the preset condition can be that the number of operating data with a clearance value less than 5m in the operating data segment is greater than 10, or it can be that the ratio of the number of operating data with a clearance value less than 5m in the operating data segment to the total number of operating data in the operating data segment reaches 50%.

[0069] It should be noted that after determining the clearance abnormality segment, a time series diagram of ten minutes before and after the clearance abnormality segment can be output, as shown in Figure 2, which can include wind speed, power, pitch angle of each of the three blades, wind angle, status of the wind turbine generator set, and clearance value. At the same time, the start time and end time of the clearance abnormality segment, the duration, the number of operating data with a clearance value less than 5m, the total number of operating data in the clearance abnormality segment, the minimum clearance value, maximum clearance value, and average clearance value in the clearance abnormality segment, the average wind speed, average power, and average pitch angle of the three blades in the clearance abnormality segment, etc. can be output in the data table. Other data can also be displayed or output, and the present disclosure does not limit this. As long as it is the data that the user needs to display and output, the user can identify whether it is a real abnormality based on this, and the clearance abnormality segment can be further verified.

[0070] In step S105, the clearance abnormality of the wind turbine generator set is determined based on the clearance abnormality segments. For example, the number of clearance abnormality segments within a predetermined time can be used to determine whether the clearance of the wind turbine generator set is abnormal, which is not limited in this disclosure.

[0071] According to an embodiment of the present disclosure, determining a clearance abnormality of a wind turbine generator set based on clearance abnormality segments may include: determining a clearance abnormality of the wind turbine generator set in response to the number of clearance abnormality segments within a predetermined time being greater than a third preset value. According to this embodiment, the number of clearance abnormality segments can be used to conveniently and quickly determine whether the clearance of the wind turbine generator set is abnormal.

[0072] Specifically, the third preset value can be set as needed, for example, to 10, or other values, which are not limited in this disclosure. For example, taking the third preset value as 10, the number of abnormal clearance segments occurring within a predetermined time period, i.e., the number of abnormal clearance segments, can be counted. If the number of abnormal clearance segments is greater than 10, a warning flag is output as 1, indicating that the wind turbine has an abnormal clearance.

[0073] It should be noted that if the method disclosed in the present invention is built into a model, the clearance abnormality diagnosis model is completed. The model can be deployed to a certain early warning platform for real-time abnormal clearance diagnosis and early warning. After receiving the early warning information (that is, the output early warning flag is 1), the wind turbine can take corresponding protective actions such as increasing the pitch angle. Project staff can also conduct tower sweep risk inspections in advance, or use it for risky machine position identification within the company. This disclosure does not limit this.

[0074] For the convenience of understanding the above embodiments, the following description is made in conjunction with FIG3 system. FIG3 is a complete flow chart showing the clearance anomaly detection of one or more embodiments of the present disclosure. As shown in FIG3, the original operating data within a predetermined time is obtained, and the integrity and validity analysis is performed based on the clearance value of the original operating data. The analysis results are output, such as output to a data table. If the original operating data is complete and valid, the clearance data correlation analysis is performed, otherwise the detection process is terminated. The clearance data correlation analysis, the specific analysis results are shown in the above embodiments, and will not be discussed in detail here. The clearance detection equipment is judged based on the analysis results to determine whether it is accurately calibrated. If the clearance detection equipment is accurately calibrated, proceed directly to the next step, i.e., abnormal clearance diagnosis. If the clearance detection equipment is not accurately calibrated, i.e., the calibration is abnormal, the detection process is terminated. During abnormal clearance diagnosis, the original operating data is first screened for data with wind speeds between 8 and 13 m / s and power between rated power * 80% and rated power * 110%, i.e., the first operating data in the aforementioned embodiment. After obtaining the first operating data, continuous segments within the operating data are identified, i.e., multiple operating data segments are obtained. After obtaining the multiple operating data segments, segments with a duration of less than 60 seconds are merged. The minimum clearance value of each merged operating data segment is then calculated to determine whether the operating data segment meets the following conditions: the minimum clearance value is less than 5 m and meets a preset condition. If so, the operating data segment is considered an abnormal clearance segment. The preset conditions are described in the aforementioned embodiment and will not be discussed further here. If the operating data segment is determined to be an abnormal clearance segment, a time sequence diagram and a statistical table of the abnormal clearance segment are output. A determination is made as to whether the abnormal clearance segment has occurred more than 10 times within a predetermined time period. If so, a warning flag is output as "yes" and the corresponding warning information is output. Otherwise, a warning flag is output as "no." This concludes the clearance detection process.

[0075] According to an embodiment of the present disclosure, the clearance anomaly detection method may further include the following steps: for each wind turbine in a wind farm including the wind turbine, based on the clearance preset value of the operating data in each power interval, obtaining a first clearance preset value curve of the corresponding wind turbine, and based on the clearance preset value of the operating data in each pitch angle interval, obtaining a second clearance preset value curve of the corresponding wind turbine, wherein the clearance preset value is a second specified clearance value, a first specified clearance value, or a clearance average value; based on the first clearance preset value curve and / or the second clearance preset value curve of all wind turbines, determining whether the wind turbine is outliers. According to this embodiment, whether the wind turbine is outliers is determined by performing a correlation analysis between the clearance value and variables such as power and pitch angle.

[0076] Specifically, based on the clearance minimum value, clearance maximum value, or clearance average value of each wind turbine generator set in different power bins / different pitch angle bins obtained in the above embodiment, it can be determined whether the wind turbine generator set is outliers. Of course, the present disclosure is not limited to the clearance minimum value, clearance maximum value, or clearance average value, and other clearance-related values ​​can also be used. For example, taking the clearance minimum value, clearance maximum value, or clearance average value as an example, after power binning and / or pitch angle binning, the clearance minimum value curve, clearance maximum value curve, or clearance average value curve corresponding to different power bins / different pitch angle bins of each wind turbine generator set can be obtained, for example, the clearance minimum value curve (min), clearance maximum value curve (max), or clearance average value curve (mean) corresponding to different power bins of a certain wind turbine generator set as shown in FIG4 , and the clearance minimum value curve (min), clearance maximum value curve (max), or clearance average value curve (mean) corresponding to different pitch angle bins of a certain wind turbine generator set as shown in FIG5 . Any one of these curves can be analyzed to determine whether a wind turbine is an outlier, or multiple curves can be analyzed simultaneously to determine whether a wind turbine is an outlier, which is not limited in this disclosure. The analysis of any one of these curves can be performed using a Local Outlier Factor (LOF) algorithm, or other algorithms, which are not limited in this disclosure.

[0077] It should be noted that the outlier of a wind turbine indicates that the corresponding clearance preset value curve is different from the clearance preset value curves of other wind turbines, but it does not necessarily mean that it is abnormal. Therefore, in general, it is necessary to pay special attention to the wind turbine and check the reason for the outlier. If it is determined that a wind turbine is outlier, a low clearance outlier warning or a high clearance outlier warning for the wind turbine in the wind farm can be triggered based on the outlier identification result. In general, the wind turbine with low clearance outliers identified may be caused by terrain factors or blade damage, and requires more attention, otherwise there may be a risk of tower sweeping or serious damage to components; the wind turbine with high clearance outliers identified may be related to the installation or calibration of the clearance detection equipment. If not corrected in time, it may affect the normal clearance value measurement.

[0078] According to an embodiment of the present disclosure, determining whether a wind turbine is an outlier based on the first predetermined clearance value curve and / or the second predetermined clearance value curve of all wind turbines may include: for each predetermined clearance value curve, determining the distance between the wind turbine and other wind turbines in the wind farm based on the predetermined clearance value curves of all wind turbines; and determining whether the wind turbine is an outlier based on the distance between the wind turbine and other wind turbines in the wind farm. According to this embodiment, by determining the distance between the wind turbine and other wind turbines in the wind farm using the predetermined clearance value curve, it is possible to conveniently and quickly determine whether a wind turbine is an outlier based on the distance.

[0079] For example, taking the minimum clearance curve after power binning as an example, FIG6 is a schematic diagram showing the minimum clearance curve of one or more embodiments of the present disclosure. As shown in FIG6, the horizontal axis represents power and the vertical axis represents the clearance value. The bottom curve is the minimum clearance curve of the wind turbine generator set in the above embodiment, and the other curves are the minimum clearance curves of other wind turbine generator sets in the wind farm. After obtaining the minimum clearance curve of each wind turbine generator set in the wind farm, the distance K between any other wind turbine generator set and the wind turbine generator set in the above embodiment can be calculated by the following formula: i :

[0080] Where x represents the vertical coordinate of the wind turbine generator set, and y represents the vertical coordinate of other wind turbine generator sets. It should be noted that if there are multiple clearance values ​​on a curve, the average of the clearance values ​​can be taken and the average value is used as the vertical coordinate of the wind turbine generator set corresponding to the curve, as shown in Figure 7, where point P represents the average clearance value of the wind turbine generator set, that is, the vertical coordinate of the wind turbine generator set, and point O represents the average clearance value of the wind turbine generator set, that is, the vertical coordinate of the wind turbine generator set. irepresents the average clearance value of the other wind turbines, i.e., the vertical coordinate of the other wind turbines. Of course, other methods can also be used. Specifically, assuming that there are three clearance values ​​in a curve, the distances corresponding to the three clearance values ​​can be calculated respectively, and then the average of the three distances obtained can be taken as the distance between the other wind turbines and the wind turbine of the above embodiment. This disclosure is not limited to this.

[0081] After obtaining the distances between other wind turbines and the wind turbine in the above embodiment, the distances between other wind turbines can also be known, and a corresponding distance set can be obtained. When the distance of the wind turbine in the above embodiment is not aggregated with other distances in the distance set, such as the distance of the wind turbine in the above embodiment exceeds most of the distances in the distance set by too much, it can be determined that the wind turbine in the above embodiment is out of the group.

[0082] According to an embodiment of the present disclosure, determining whether a wind turbine is out of the group based on the distance between the wind turbine and other wind turbines in the wind farm may include: obtaining an average value of the distance between the predetermined wind turbine and the wind turbine, wherein the predetermined wind turbine is the wind turbine ranked before the predetermined ranking among the other wind turbines after being sorted by the distance from the wind turbine; obtaining the local reachable density of the wind turbine based on the correlation data of the average value; and determining whether the wind turbine is out of the group based on the local reachable density of the wind turbine and the local reachable density of the predetermined wind turbine. According to this embodiment, the local reachable density of each wind turbine is further obtained by the distance between the other wind turbines and the wind turbine, and based on the local reachable density, it is possible to relatively accurately determine whether the wind turbine is out of the group.

[0083] For example, still taking the minimum clearance curve after power binning as an example, we first define the inverse of the average reachable distance between point P and its neighboring points as the local reachable density, which can be recorded as lrd(p). At this time, in order to obtain the distance between point P and other points O i To obtain the local reachability density of a point, we need to obtain the K-neighboring distance of each point. Taking point P as an example, assuming K = 3, we need to obtain the distance between the third point closest to point P and point P, that is, the K-neighboring distance of point P, which can be recorded as k-distance(p), as shown in Figure 8, where k-distance(O1) is the K-neighboring distance of point O1. After obtaining k-distance(p), we can obtain the local reachability density lrd(p) of point P, as shown in Figure 9:

[0084] After obtaining the local reachable density of the wind turbine generator set in the above embodiment, that is, the local reachable density of point P, a similar method can be used to obtain the local reachable density of the predetermined wind turbine generator set in the above embodiment. When the local reachable density of point P is less than a certain value of the local reachable density of the predetermined wind turbine generator set, it can be determined that the wind turbine generator set corresponding to point P is an outlier. Of course, the local reachable densities of all other wind turbine generator sets can also be obtained. In this case, when the local reachable density of point P is less than a certain value of the local reachable density of all other wind turbine generator sets, it can be determined that the wind turbine generator set corresponding to point P is an outlier.

[0085] According to an embodiment of the present disclosure, determining whether a wind turbine is outliers based on the local reachable density of the wind turbine and the local reachable density of a predetermined wind turbine may include: obtaining the local reachable density of the predetermined wind turbine; obtaining a local abnormality factor of the wind turbine based on the local reachable density of the wind turbine and the local reachable density of the predetermined wind turbine; and determining that the wind turbine is outliers in response to a difference between the local abnormality factor and a sixth preset value exceeding a preset threshold. According to this embodiment, based on obtaining the local reachable density, the local abnormality factor of the wind turbine is further obtained based on the local reachable density, thereby more accurately determining whether the wind turbine is outliers.

[0086] For example, still taking the minimum headroom curve after power binning as an example, we first define the ratio of the average local reachability density of the neighboring points of point P to the local reachability density of point P as the local outlier factor of point P, that is, LOF(P). Assuming that the neighboring points of point P are O1, O2, and O3, as shown in Figure 10, the local outlier factor of point P is LOF(P):

[0087] After obtaining the local outlier factor LOF(P) of point P, if LOF(P) is close to 1, it means that the wind turbine corresponding to point P is very close to the neighboring area; if LOF(P) is less than 1, it means that the wind turbine corresponding to point P is in a relatively dense area and is less likely to be an outlier; if LOF(P) is much greater than 1, it means that the wind turbine corresponding to point P is far away from other wind turbines and is very likely to be an outlier, as shown in Figures 11 and 12.

[0088] For the convenience of understanding the above embodiment, the following description is made in conjunction with FIG13 system. FIG13 is a complete flow chart showing outlier identification of one or more embodiments of the present disclosure. As shown in FIG13 , a clearance data correlation analysis is performed on each wind turbine generator set. For details, see the above embodiment, which will not be discussed in detail here. After the clearance data correlation analysis, the clearance minimum / maximum curve of each wind turbine generator set under different power bins or the clearance minimum / maximum curve of each wind turbine generator set under different pitch angle bins can be obtained. The outlier analysis is performed using the LOF algorithm. According to the analysis results, it is determined whether there are outlier wind turbine generator sets. Any curve can be used to determine the outlier, and then it is determined that there is an outlier unit. Multiple curves can also be used to determine the outlier at the same time to determine that there is an outlier unit. If it is determined that there is an outlier unit, an outlier warning is output. If it is determined that there is no outlier unit, the process is terminated.

[0089] In summary, the present disclosure can combine the clearance value of time series data (i.e., operating data within a predetermined time) within a period of time with the correlation analysis of key variables to obtain the clearance distribution law and clearance change trend, so that the time when the clearance abnormality occurs can be known, and then when the clearance abnormality occurs, the clearance risk can be predicted in advance. The results model of the present disclosure can be deployed to the farm group monitoring system or other systems that communicate with the wind turbine generator set for real-time abnormal clearance diagnosis and farm-level clearance outlier identification. After receiving the early warning information, the wind turbine generator set can take corresponding protective actions such as raising the pitch angle, or preventive inspection of large components and clearance equipment. The results model of the present disclosure can also be deployed to the early warning platform for single-machine abnormal clearance diagnosis and early warning and farm group clearance outlier identification and early warning. After receiving the early warning information, the project staff can do tower sweep risk or large component risk inspection in advance. The results model of the present disclosure can also be deployed to the big data platform for risk machine position investigation and formation of risk unit ledgers including but not limited to risk conditions, risk units, and risk terrain, so as to deploy preventive risks in advance and avoid causing greater economic losses.

[0090] Figure 14 is a block diagram showing a clearance anomaly detection device for a wind turbine generator set according to one or more embodiments of the present disclosure. As shown in Figure 14 , the device includes a first acquisition unit 140 , a second acquisition unit 142 , a grouping unit 144 , a first determination unit 146 , and a second determination unit 148 .

[0091] The first acquisition unit 140 is configured to acquire the operating data of the wind turbine generator set within a predetermined time; the second acquisition unit 142 is configured to acquire first operating data with a wind speed within a predetermined wind speed range and a power within a predetermined power range from the operating data; the grouping unit 144 is configured to divide the first operating data into operating data segments; the first determination unit 146 is configured to, for each operating data segment, determine the operating data segment as a clearance abnormality segment if a first specified clearance value in the operating data segment is less than a first preset value and the operating data segment meets a preset condition, wherein the preset condition is associated with the number of operating data in the operating data segment whose clearance value is less than the first preset value; the second determination unit 148 is configured to determine the clearance abnormality of the wind turbine generator set based on the clearance abnormality segment.

[0092] According to an embodiment of the present disclosure, the preset conditions include one of the following: the number of running data items whose clearance value in the running data segment is less than the first preset value is greater than the second preset value; the ratio of the number of running data items whose clearance value in the running data segment is less than the first preset value to the total number of running data items in the running data segment reaches a first predetermined ratio.

[0093] According to an embodiment of the present disclosure, the second determining unit 148 is further configured to determine that the clearance of the wind turbine generator set is abnormal in response to the number of clearance abnormality segments within the predetermined time being greater than a third preset value.

[0094] According to an embodiment of the present disclosure, the second acquisition unit 142 is further configured to perform power binning on the operating data before obtaining first operating data with a wind speed within a predetermined wind speed range and a power within a predetermined power range from the operating data, so as to divide the operating data into multiple power intervals and obtain a second specified clearance value of the operating data in each power interval; in response to the fact that within the predetermined power range, the ratio of the number of power intervals with the second specified clearance value within the first predetermined range to the total number of power intervals within the predetermined power range reaches a second predetermined ratio, and it is determined that the first clearance detection device flag indicates that there is no abnormality in the calibration of the clearance detection device.

[0095] According to an embodiment of the present disclosure, the second acquisition unit 142 is further configured to perform angle binning on the operating data before acquiring first operating data in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range from the operating data, so as to divide the operating data into multiple pitch angle intervals, and obtain a second specified clearance value of the operating data in each pitch angle interval; in response to the fact that within the range of the minimum pitch angle to the predetermined degree, the ratio of the number of pitch angle intervals with the second specified clearance value within the first predetermined range to the total number of pitch angle intervals within the range of the minimum pitch angle to the predetermined degree reaches a second predetermined ratio, it is determined that the second clearance detection device flag indicates that there is no abnormality in the calibration of the clearance detection device.

[0096] According to an embodiment of the present disclosure, the second acquiring unit 142 is further configured to determine that there is no abnormality in the clearance detection device calibration in response to both the first clearance detection device flag and the second clearance detection device flag indicating that there is no abnormality in the clearance detection device calibration.

[0097] According to an embodiment of the present disclosure, the second acquisition unit 142 is further configured to, in response to a calibration abnormality of the clearance detection device, obtain a first specified clearance value of the operating data within each power interval; in response to the fact that within the predetermined power range, the ratio of the number of power intervals with the first specified clearance value within the second predetermined range to the total number of power intervals within the predetermined power range reaches a third predetermined ratio, determine that the first clearance value flag indicates that there is no abnormality in the clearance value; otherwise, determine that the wind turbine generator set is predicted to have a low clearance risk and issue a prompt message to immediately calibrate the clearance detection device.

[0098] According to an embodiment of the present disclosure, the second acquisition unit 142 is further configured to, in response to a calibration abnormality of the clearance detection device, obtain a first specified clearance value of the operating data within each pitch angle interval; in response to the fact that, within the range from the minimum pitch angle to the predetermined degree, the ratio of the number of pitch angle intervals with the first specified clearance value within the second predetermined range to the total number of pitch angle intervals within the range from the minimum pitch angle to the predetermined degree reaches a third predetermined ratio, determine that the second clearance value flag indicates that there is no abnormality in the clearance value; otherwise, determine that the wind turbine generator set predicts a low clearance risk and issue a prompt message to immediately calibrate the clearance detection device.

[0099] According to an embodiment of the present disclosure, the second acquisition unit 142 is further configured to determine that the clearance value is normal in response to the first clearance value flag and the second clearance value flag both indicating that the clearance value is normal; otherwise, it is determined that the wind turbine generator set is predicted to have a low clearance risk and a prompt message is issued to immediately calibrate the clearance detection equipment.

[0100] According to an embodiment of the present disclosure, the second acquisition unit 142 is further configured to obtain second operating data with a clearance value within a third predetermined range from the operating data; obtain the sum of the duration of each operating data in the second operating data as the first duration; obtain the duration between the start time and the end time of the operating data as the second duration; and in response to the first duration and the second duration satisfying the integrity condition, obtain first operating data with a wind speed within a predetermined wind speed range and a power within a predetermined power range from the operating data.

[0101] According to an embodiment of the present disclosure, the second acquisition unit 142 is further configured to acquire, from the operating data, third operating data that is in a grid-connected state and has a clearance value greater than a fourth preset value and less than a fifth preset value; the sum of the duration of each operating data in the third operating data is used as the third duration; the duration between the start time and the end time of the operating data is acquired as the second duration, wherein the second operating data is operating data in which the clearance value in the operating data is within a third predetermined range; in response to the third duration and the second duration satisfying the validity condition, first operating data in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range is acquired from the operating data.

[0102] According to an embodiment of the present disclosure, the grouping unit 144 is further configured to obtain, for each running data segment, the duration between the start time and the end time of the running data segment as the duration of the running data segment; when the sum of the durations of a predetermined number of consecutive running data segments is less than the predetermined duration, merge the predetermined number of running data segments, and use the merged running data segments to replace the predetermined number of running data segments.

[0103] According to an embodiment of the present disclosure, an outlier determination unit is configured to, for each wind turbine in a wind farm including the wind turbines, obtain, based on a predetermined clearance value of operating data within each power interval, a first predetermined clearance value curve of the corresponding wind turbine, and obtain, based on the predetermined clearance value of operating data within each pitch angle interval, a second predetermined clearance value curve of the corresponding wind turbine, wherein the predetermined clearance value is a second specified clearance value, a first specified clearance value, or a clearance average value; and determine whether a wind turbine is outlier based on the first predetermined clearance value curves and / or the second predetermined clearance value curves of all wind turbines.

[0104] According to an embodiment of the present disclosure, the outlier determination unit is further configured to determine, for each predetermined clearance value curve, the distance between other wind turbines in the wind farm and the wind turbine based on the predetermined clearance value curves of all wind turbines; and determine whether the wind turbine is outliers based on the distance between other wind turbines in the wind farm and the wind turbine.

[0105] According to an embodiment of the present disclosure, the outlier determination unit is further configured to obtain an average value of the distance between a predetermined wind turbine and the wind turbine, wherein the predetermined wind turbine is a wind turbine that is ranked before a predetermined ranking among other wind turbines after being sorted by the distance from the wind turbine; obtain a local reachable density of the wind turbine based on associated data of the average value; and determine whether the wind turbine is an outlier based on the local reachable density of the wind turbine and the local reachable density of the predetermined wind turbine.

[0106] According to an embodiment of the present disclosure, the outlier determination unit is further configured to obtain the local reachable density of a predetermined wind turbine generator set; obtain the local abnormality factor of the wind turbine generator set based on the local reachable density of the wind turbine generator set and the local reachable density of the predetermined wind turbine generator set; and determine that the wind turbine generator set is outlier in response to the difference between the local abnormality factor and the sixth preset value exceeding a preset threshold.

[0107] According to an embodiment of the present disclosure, a computer-readable storage medium storing instructions is provided, wherein when the instructions are executed by at least one computing device, the at least one computing device is prompted to execute the wind turbine clearance anomaly detection method as described in any of the above embodiments.

[0108] According to an embodiment of the present disclosure, a system is provided comprising at least one computing device and at least one storage device storing instructions, wherein the instructions, when executed by the at least one computing device, prompt the at least one computing device to execute a clearance anomaly detection method for a wind turbine generator set as described in any of the above embodiments.

[0109] In another general aspect, a wind turbine generator set is provided, comprising the above-mentioned clearance anomaly detection device for the wind turbine generator set.

[0110] While some embodiments of the present disclosure have been shown and described, it will be appreciated by those skilled in the art that changes may be made to these embodiments without departing from the principles and spirit of the disclosure, the scope of which is defined by the claims and their equivalents.

Claims

1. A method for detecting abnormal clearance of a wind turbine generator set, characterized in that: include: Obtaining the operation data of the wind turbine generator set within a predetermined time; From the operation data, first operation data is obtained in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range; dividing the first operation data into a plurality of operation data segments; For each operation data segment, when a first designated clearance value in the operation data segment is less than a first preset value and the operation data segment satisfies a preset condition, the operation data segment is determined as a clearance abnormal segment, wherein the preset condition is associated with the number of operation data in the operation data segment whose clearance value is less than the first preset value; A clearance abnormality of the wind turbine generator set is determined according to the clearance abnormality segment.

2. The clearance anomaly detection method according to claim 1, characterized in that: The preset condition includes one of the following: The number of pieces of operating data in the operating data segment whose clearance value is less than the first preset value is greater than a second preset value; The ratio of the number of operating data in the operating data segment whose clearance value is less than the first preset value to the total number of operating data in the operating data segment reaches a first predetermined ratio.

3. The clearance anomaly detection method according to claim 1, characterized in that: Determining the clearance abnormality of the wind turbine generator set according to the clearance abnormality segment includes: In response to the number of clearance abnormality segments within the predetermined time being greater than a third preset value, it is determined that the clearance of the wind turbine generator set is abnormal.

4. The clearance anomaly detection method according to claim 1, characterized in that: Before acquiring first operating data in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range from the operating data, the method further includes: Performing power binning on the operating data to divide the operating data into a plurality of power intervals and obtaining a second specified headroom value of the operating data in each power interval; In response to the fact that within the predetermined power range, the ratio of the number of power intervals of the second specified clearance value within the first predetermined range to the total number of power intervals within the predetermined power range reaches a second predetermined ratio, it is determined that the first clearance detection device flag indicates that there is no abnormality in the calibration of the clearance detection device.

5. The clearance anomaly detection method according to claim 1, characterized in that: Before acquiring first operating data in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range from the operating data, the method further includes: Performing angle binning on the operating data to divide the operating data into a plurality of pitch angle intervals, and obtaining a second designated clearance value of the operating data in each pitch angle interval; In response to the fact that, within the range from the minimum pitch angle to the predetermined degree, the ratio of the number of pitch angle intervals of the second specified clearance value within the first predetermined range to the total number of pitch angle intervals within the range from the minimum pitch angle to the predetermined degree reaches a second predetermined ratio, it is determined that the second clearance detection device flag indicates that there is no abnormality in the calibration of the clearance detection device.

6. The clearance anomaly detection method according to claim 4 or 5, characterized in that: Also includes: In response to the first clearance detection device flag and the second clearance detection device flag both indicating that the clearance detection device calibration is normal, it is determined that the clearance detection device calibration is normal.

7. The clearance anomaly detection method according to claim 1, characterized in that: Also includes: In response to a calibration anomaly of the headroom detection device, obtaining a first specified headroom value of the operating data in each power interval; In response to the fact that, within the predetermined power range, the ratio of the number of power intervals of the first specified clearance value within the second predetermined range to the total number of power intervals within the predetermined power range reaches a third predetermined ratio, it is determined that the first clearance value flag indicates that there is no abnormality in the clearance value; otherwise, it is determined that the wind turbine generator set predicts a low clearance risk and a prompt message is issued to immediately calibrate the clearance detection device.

8. The clearance anomaly detection method according to claim 1, characterized in that: Also includes: In response to a calibration anomaly of the clearance detection device, obtaining a first specified clearance value of the operating data in each pitch angle interval; In response to the fact that, within the range from the minimum pitch angle to the predetermined degree, the ratio of the number of pitch angle intervals of the first specified clearance value within the second predetermined range to the total number of pitch angle intervals within the range from the minimum pitch angle to the predetermined degree reaches a third predetermined ratio, it is determined that the second clearance value flag indicates that there is no abnormality in the clearance value; otherwise, it is determined that the wind turbine generator set predicts a low clearance risk and a prompt message is issued to immediately calibrate the clearance detection device.

9. The clearance anomaly detection method according to claim 7 or 8, characterized in that: Also includes: In response to the first clearance value flag and the second clearance value flag both indicating that the clearance value is normal, it is determined that the clearance value is normal; otherwise, it is determined that the wind turbine generator set is predicted to have a low clearance risk and a prompt message is issued to immediately calibrate the clearance detection device.

10. The clearance anomaly detection method according to claim 1, characterized in that: The obtaining, from the operation data, first operation data in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range comprises: acquiring, from the operating data, second operating data having a clearance value within a third predetermined range; Obtaining the sum of the durations of each piece of operation data in the second operation data as the first duration; Obtaining the duration between the start time and the end time of the operation data as the second duration; In response to the first duration and the second duration satisfying the integrity condition, first operating data in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range is acquired from the operating data.

11. The clearance anomaly detection method according to claim 1, characterized in that: The obtaining, from the operation data, first operation data in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range comprises: From the operation data, third operation data in a grid-connected state and having a headroom value greater than a fourth preset value and less than a fifth preset value is obtained; The sum of the duration of each piece of operation data in the third operation data is used as the third duration; Obtaining the duration between the start time and the end time of the operation data as the second duration; In response to the third time period and the second time period satisfying the validity condition, first operation data with a wind speed within a predetermined wind speed range and a power within a predetermined power range is acquired from the operation data.

12. The clearance anomaly detection method according to claim 1, characterized in that: Also includes: For each operation data segment, obtaining the duration between the start time and the end time of the operation data segment as the duration of the operation data segment; When the sum of the durations of a predetermined number of consecutive operation data segments is less than the predetermined duration, the predetermined number of operation data segments are merged, and the merged operation data segments are used to replace the predetermined number of operation data segments.

13. The clearance anomaly detection method according to claim 6, characterized in that: Also includes: For each wind turbine generator set in the wind farm including the wind turbine generator set, based on the clearance preset value of the operating data in each power interval, a first clearance preset value curve of the corresponding wind turbine generator set is obtained, and based on the clearance preset value of the operating data in each pitch angle interval, a second clearance preset value curve of the corresponding wind turbine generator set is obtained, wherein the clearance preset value is the second designated clearance value, the first designated clearance value or the clearance average value; Based on the first predetermined clearance value curves and / or the second predetermined clearance value curves of all wind turbines, it is determined whether the wind turbine is out of the group.

14. The clearance anomaly detection method according to claim 13, characterized in that: The determining whether the wind turbine generator set is out of the group based on the first clearance preset value curve and / or the second clearance preset value curve of all wind turbine generator sets comprises: For each clearance preset value curve, based on the clearance preset value curves of all wind turbines, determining the distance between the wind turbine and other wind turbines in the wind farm; Whether the wind turbine generator set is out of the group is determined based on the distance between the wind turbine generator set and other wind turbine generator sets in the wind farm.

15. The clearance anomaly detection method according to claim 14, characterized in that: The determining whether the wind turbine generator set is out of the group based on the distance between the wind turbine generator set and other wind turbine generator sets in the wind farm comprises: Obtaining an average value of the distance between a predetermined wind turbine generator set and the wind turbine generator set, wherein the predetermined wind turbine generator set is a wind turbine generator set before a predetermined ranking among the other wind turbine generator sets after being sorted by distance from the wind turbine generator set; Based on the associated data of the average value, a local reachable density of the wind turbine generator set is obtained; Based on the local reachable density of the wind turbine generator set and the local reachable density of the predetermined wind turbine generator set, it is determined whether the wind turbine generator set is out of the group.

16. The clearance anomaly detection method according to claim 15, characterized in that: The determining whether the wind turbine generator set is out of the group based on the local reachable density of the wind turbine generator set and the local reachable density of the predetermined wind turbine generator set comprises: Obtaining the local reachable density of the predetermined wind turbine generator set; Based on the local reachable density of the wind turbine generator set and the local reachable density of the predetermined wind turbine generator set, a local abnormality factor of the wind turbine generator set is obtained; In response to a difference between the local abnormal factor and a sixth preset value exceeding a preset threshold, it is determined that the wind turbine generator set is out of group.

17. A clearance anomaly detection device for a wind turbine generator set, characterized in that: include: A first acquisition unit is configured to acquire operation data of the wind turbine generator set within a predetermined time; A second acquisition unit is configured to acquire first operation data, in which the wind speed is within a predetermined wind speed range and the power is within a predetermined power range, from the operation data; a grouping unit, configured to divide the first operation data into operation data segments; The first determining unit is configured to, for each operation data segment, determine the operation data segment as a clearance abnormal segment when a first specified clearance value in the operation data segment is less than a first preset value and the operation data segment satisfies a preset condition, wherein the preset condition is the same as the clearance abnormality value. The number of pieces of operating data in the operating data segment whose clearance value is less than the first preset value is associated; The second determining unit is configured to determine the clearance abnormality of the wind turbine generator set according to the clearance abnormality segment.

18. A computer-readable storage medium storing instructions, characterized in that: When the instructions are executed by at least one computing device, the at least one computing device is prompted to execute the clearance abnormality detection method for a wind turbine generator set according to any one of claims 1 to 16.

19. A system comprising at least one computing device and at least one storage device storing instructions, characterized in that: When the instructions are executed by the at least one computing device, the at least one computing device is prompted to execute the clearance anomaly detection method for a wind turbine generator set according to any one of claims 1 to 16.

20. A wind turbine generator set, characterized in that: Includes the clearance abnormality detection device as described in claim 17.

Images