Method and apparatus for predicting a variable pitch failure of a wind turbine generator system

Abstract

Provided are a method and device for predicting a variable pitch failure of a wind turbine, the method comprising: obtaining a variable pitch speed of each blade of the wind turbine and an active power of the wind turbine at each sampling time during a variable pitch operation of the wind turbine; determining a power interval in which the active power of the wind turbine at each sampling time is located, and determining whether a variable pitch speed difference of each two blades at each sampling time exceeds a corresponding variable pitch speed difference range based on a mapping relationship between the variable pitch speed difference range and the power interval; and outputting first variable pitch failure warning information indicating that a variable pitch failure occurs when a number of variable pitch speed differences of each two blades that exceed the corresponding variable pitch speed difference range is greater than a first preset number.

Description

Technical Field

[0001] This application relates to the field of wind power generation technology, and more specifically, to a method and apparatus for predicting pitch faults in wind turbine generator sets. Background Technology

[0002] Wind turbine generators typically perform pitch control under the control of a master control logic. Under normal circumstances, the pitch control actions of multiple blades of a wind turbine generator should be consistent. When a pitch failure occurs due to damage to components such as toothed belts or pitch motor brakes, it will lead to inconsistent pitch control actions. This can affect power generation or, in severe cases, cause damage to components of the wind turbine generator due to aerodynamic imbalance.

[0003] In related technologies, pitch faults are determined by detecting whether the difference between the pitch angles of different blades exceeds a threshold. However, when it is determined that the difference exceeds the threshold, the fault has already occurred. It is evident that this approach cannot predict whether a pitch fault will occur so as to notify the user to take timely maintenance measures.

[0004] Therefore, there is an urgent need for a method and device for predicting pitch failures in wind turbine generator sets to predict the occurrence of pitch failures in advance, so that users can take timely maintenance measures to avoid major losses. Summary of the Invention

[0005] The purpose of this invention is to provide a method and apparatus for predicting pitch faults in wind turbine generator sets, so as to at least solve the problems in the above-mentioned related technologies, or it may not solve any of the above-mentioned problems.

[0006] According to one aspect of the embodiments of this disclosure, a pitch fault prediction method for a wind turbine generator set is provided. The pitch fault prediction method includes: during the pitch operation of the wind turbine generator set, acquiring the pitch speed of each blade of the wind turbine generator set and the active power of the wind turbine generator set at each sampling time; determining the power range in which the active power of the wind turbine generator set is located at each sampling time, and determining whether the pitch speed difference between each pair of blades exceeds the corresponding pitch speed difference range based on the mapping relationship between the pitch speed difference range between each pair of blades and the power range; and when the number of pitch speed differences between each pair of blades exceeding the corresponding pitch speed difference range is greater than a first preset number, outputting a first pitch fault warning message indicating that a pitch fault has occurred.

[0007] Optionally, the mapping relationship is obtained by: dividing the pitch speed of the blades of multiple wind turbine generator sets during pitch operation into data compartments according to power ranges; for any given power range, calculating the pitch speed difference between every two blades of each of the multiple wind turbine generator sets; and for any given power range, determining the pitch speed difference range between every two blades corresponding to the given power range based on the pitch speed difference between every two blades of each wind turbine generator set, wherein the multiple wind turbine generator sets are of the same type as the wind turbine generator sets.

[0008] Optionally, for any given power range, the step of determining the pitch speed difference range between two blades corresponding to the given power range based on the pitch speed difference between two blades of each wind turbine generator set includes: calculating the average pitch speed difference between two blades of each wind turbine generator set; adding a first preset increment to the average value as the upper limit of the pitch speed difference range between two blades corresponding to the given power range; and subtracting the first preset increment from the average value as the lower limit of the pitch speed difference range between two blades corresponding to the given power range.

[0009] According to another aspect of the embodiments of this disclosure, a pitch fault prediction method for a wind turbine generator set is provided. The method further includes: during the pitch operation of the wind turbine generator set, acquiring the pitch angle of each blade of the wind turbine generator set and the active power of the wind turbine generator set at each sampling time; determining the power range in which the active power of the wind turbine generator set is located at each sampling time, and determining whether the pitch angle difference between each pair of blades exceeds the corresponding pitch angle difference range based on the mapping relationship between the pitch angle difference range of each pair of blades and the power range; and when the number of pitch angle differences between each pair of blades exceeding the corresponding pitch angle difference range is greater than a second preset number, outputting a second pitch fault warning message indicating the occurrence of a pitch fault.

[0010] Optionally, the mapping relationship between the pitch angle difference range and the power range is obtained in the following way: according to the power range, the pitch angle of the blades of multiple wind turbine generator sets during pitch operation is divided into data compartments; for any power range, the pitch angle difference between every two blades of each of the multiple wind turbine generator sets is calculated; and for any power range, the pitch angle difference range between every two blades corresponding to the arbitrary power range is determined based on the pitch angle difference between every two blades of each wind turbine generator set.

[0011] Optionally, for any given power range, the step of determining the pitch angle range corresponding to the given power range based on the pitch angle difference between every two blades of each wind turbine generator set includes: calculating the average value of the pitch angle difference between every two blades of each wind turbine generator set; adding a second preset increment to the average value as the upper limit of the pitch angle difference range between every two blades corresponding to the given power range; and subtracting the second preset increment from the average value as the lower limit of the pitch angle difference range between every two blades corresponding to the given power range.

[0012] According to another aspect of the embodiments of this disclosure, a pitch fault prediction device for a wind turbine generator set is provided. The pitch fault prediction device includes: a data acquisition unit configured to acquire the pitch speed of each blade of the wind turbine generator set and the active power of the wind turbine generator set at each sampling time during the pitch operation of the wind turbine generator set; a determination unit configured to determine the power range in which the active power of the wind turbine generator set is located at each sampling time, and determine whether the pitch speed difference between each pair of blades exceeds the corresponding pitch speed difference range based on the mapping relationship between the pitch speed difference range between each pair of blades and the power range; and an output unit configured to output a first pitch fault warning message indicating that a pitch fault has occurred when the number of pitch speed differences between each pair of blades exceeding the corresponding pitch speed difference range is greater than a first preset number.

[0013] According to another aspect of the embodiments of this disclosure, a pitch fault prediction device for a wind turbine generator set is provided. The pitch fault prediction device includes: a data acquisition unit configured to acquire the pitch angle of each blade of the wind turbine generator set and the active power of the wind turbine generator set at each sampling time during the pitch operation of the wind turbine generator set; a determination unit configured to determine the power range in which the active power of the wind turbine generator set is located at each sampling time, and determine whether the pitch angle difference between each pair of blades exceeds the corresponding pitch angle difference range at each sampling time based on the mapping relationship between the pitch angle difference range between each pair of blades and the power range; and an output unit configured to output a second pitch fault warning message indicating that a pitch fault has occurred when the number of pitch angle differences between each pair of blades exceeding the corresponding pitch angle difference range is greater than a second preset number.

[0014] According to another aspect of the embodiments of this disclosure, a computer-readable storage medium storing a computer program is provided, characterized in that, when the computer program is executed by a processor, it implements the pitch fault prediction method for wind turbine generator sets as described in this invention.

[0015] According to another aspect of the embodiments of this disclosure, a controller is provided, the controller comprising: a processor; and a memory storing a computer program, which, when executed by the processor, implements the pitch fault prediction method for wind turbine generator sets as described in this invention.

[0016] In related technologies, there is no solution for predicting pitch failures using pitch speed data. Large differences in pitch speed can indicate impending failures, but the pitch failure prediction method and apparatus according to embodiments of this disclosure can provide early warnings of pitch failures based on pitch speed data. Furthermore, since the difference in pitch speed between different blades has different safety margins when the wind turbine performs pitch control in different power ranges, using different judgment thresholds depending on the power range the wind turbine is in during pitch control can more accurately predict the occurrence of pitch failures, thereby reducing the probability of false pitch failure reports.

[0017] According to embodiments of this disclosure, since the pitch angle difference between different blades has different safety margins when the wind turbine performs pitch control in different power ranges, the pitch fault prediction method and apparatus according to embodiments of this disclosure adopt different judgment thresholds according to the different power ranges in which the wind turbine is located during pitch control, which can more accurately predict the occurrence of pitch faults, thereby reducing the probability of false pitch fault reports. Attached Figure Description

[0018] The above and other objects and features of the invention will become clearer from the following description taken in conjunction with the accompanying drawings, which exemplarily illustrate embodiments of the invention, wherein:

[0019] Figure 1 A flowchart of a wind turbine pitch fault prediction method according to an embodiment of the present disclosure is shown;

[0020] Figure 2 It is a graph showing the pitch speed data of multiple wind turbine generators in a certain wind farm during the pitch control period;

[0021] Figure 3 A flowchart of a pitch fault prediction method for a wind turbine generator set according to another embodiment of the present disclosure is shown;

[0022] Figure 4 It is a graph showing the pitch angle data of multiple wind turbine generators in a wind farm during pitch control; and

[0023] Figure 5 This is a block diagram illustrating the structure of a wind turbine pitch fault prediction device according to an embodiment of the present disclosure. Detailed Implementation

[0024] In the following description, various embodiments of the present disclosure are illustrated with reference to the accompanying drawings, wherein the same reference numerals are used to denote the same or similar elements, features, and structures. However, the present disclosure is not intended to be limited to the specific embodiments described herein, and it is intended that the present disclosure cover all modifications, equivalents, and / or substitutions of the present disclosure, provided they fall within the scope of the appended claims and their equivalents. The terms and words used in the following description and claims are not limited to their dictionary meanings, but are used only to enable a clear and consistent understanding of the present disclosure. Therefore, it will be apparent to those skilled in the art that the following description of various embodiments of the present disclosure is for illustrative purposes only and is not intended to limit the purpose of the present disclosure as defined by the appended claims and their equivalents.

[0025] It should be understood that, unless the context clearly indicates otherwise, the singular form includes the plural form. The terms “comprising,” “including,” and “having” as used herein indicate the presence of a disclosed function, operation, or element, but do not exclude other functions, operations, or elements.

[0026] For example, the expression “A or B” or “at least one of A and / or B” can indicate A and B, or A or B. For example, the expression “A or B” or “at least one of A and / or B” can indicate (1) A, (2) B or (3) both A and B.

[0027] In various embodiments of this disclosure, it is intended that when a component (e.g., a first component) is referred to as being "coupled" or "connected" to, or being "coupled" or "connected" to, another component (e.g., a second component), the component may be directly connected to, or may be connected via, another component (e.g., a third component). Conversely, when a component (e.g., a first component) is referred to as being "directly coupled" or "directly connected" to, or being directly coupled to or directly connected to, another component (e.g., a second component), there is no other component (e.g., a third component) between the component and the other component.

[0028] The expression “configured as” used in describing the various embodiments of this disclosure may be used interchangeably, for example, with expressions such as “suitable for,” “capable of,” “designed to,” “suitable for,” “manufactured as,” and “capable,” depending on the context. The term “configured as” may not necessarily indicate that the hardware is “specifically designed for.” Rather, in some cases, the expression “a device configured as…” may indicate that the device and another device or part of it are “capable of…”. For example, the expression “a processor configured to perform A, B, and C” may indicate a dedicated processor (e.g., an embedded processor) for performing the respective operations or a general-purpose processor (e.g., a central processing unit CPU or application processor (AP)) for performing the respective operations by executing at least one software program stored in a memory device.

[0029] The terminology used herein is intended to describe certain embodiments of this disclosure but is not intended to limit the scope of other embodiments. Unless otherwise stated herein, all terms used herein (including technical or scientific terms) are to have the same meaning as commonly understood by one of ordinary skill in the art. Generally, terms as defined in dictionaries should be considered to have the same meaning as in the context of the relevant field and should not be interpreted differently or as having an overly formal meaning unless expressly defined herein. In no event should the terminology defined in this disclosure be construed as excluding embodiments of this disclosure.

[0030] Modern wind turbines primarily use variable pitch rotors. When pitch is adjusted, the vertical projection of the wind turbine blades onto the ground changes. When the blades are perpendicular to the ground, the pitch angle is 0 degrees; when the blades are parallel to the ground, the pitch angle is 90 degrees. Adjusting the pitch angle from 90 degrees to 0 degrees is called pitch control, and vice versa. The pitch control systems of wind turbine blades are generally independent, but are uniformly controlled by a central control unit to ensure consistent blade pitch angles.

[0031] In existing technology, the pitch control system monitors the pitch angle voltage signal through deployed position sensors. When the maximum difference in the blade pitch angle exceeds, for example, 4°, the sensor will feed back the abnormal information to the PLC system. The control platform receives the abnormal signal, analyzes it, and reports the specific fault information.

[0032] However, current technology lacks a scheme for early warning based on blade pitch angle and pitch speed data during the pitch control process of wind turbine generators. According to existing technologies, once an alarm is triggered, a fault has already occurred. Furthermore, monitoring the blade pitch angle using position sensors cannot reflect anomalies in pitch speed. For example, although the pitch angle may be consistent after pitch control, an abnormal pitch speed during the pitch control process could indicate a problem with related components. Because there is no monitoring of pitch speed, timely warnings cannot be provided.

[0033] In addition, existing technologies use the same criteria to determine whether the pitch angle exceeds a threshold when judging whether a wind turbine has a pitch fault, for different active power ranges.

[0034] However, based on a large amount of collected operating data of wind turbine generator sets, the inventors discovered that when wind turbine generator sets operate in different active power ranges and perform pitch control, the pitch angle difference and / or pitch speed difference between each pair of blades of the wind turbine generator set have different safe variation ranges. Therefore, they conceived of using different judgment criteria to determine whether the pitch angle difference and / or pitch speed difference exceed the corresponding safety margin for different active power ranges, in order to reduce the probability of false alarms and more accurately predict the occurrence of pitch failures. This allows maintenance personnel to troubleshoot and maintain the wind turbine generator sets in a timely manner.

[0035] Figure 1 A flowchart of a wind turbine pitch fault prediction method according to an embodiment of the present disclosure is shown.

[0036] Reference Figure 1 In step S101, during the pitch operation of the wind turbine generator set, the pitch speed of each blade of the wind turbine generator set and the active power of the wind turbine generator set are acquired at each sampling time.

[0037] As an example, the pitch speed of each blade of the wind turbine and the active power of the wind turbine can be obtained at each sampling time through a supervisory control and data acquisition (SCADA) system.

[0038] For ease of description, the pitch fault prediction method of this disclosure is described using a three-bladed wind turbine as an example. Those skilled in the art will understand that the pitch fault prediction method and apparatus described in this disclosure are applicable to pitch fault prediction in single-rotor (or impeller) wind turbines and multi-rotor (or impeller) wind turbines where each rotor (or impeller) includes an additional number of blades.

[0039] In step S102, the power range of the active power of the wind turbine generator at each sampling time is determined, and based on the mapping relationship between the pitch speed difference range of each pair of blades and the power range, it is determined whether the pitch speed difference of each pair of blades at each sampling time exceeds the corresponding pitch speed difference range.

[0040] As an example, the range of active power that a wind turbine can output can be divided into multiple power ranges according to the active power of the wind turbine.

[0041] As an example, the range of active power that a wind turbine can output can be divided into multiple power ranges.

[0042] As an example, the mapping relationship between the pitch speed difference range of each pair of blades and the power range can be stored in the form of a mapping table.

[0043] Table 1 shows an example of the mapping relationship between the pitch speed difference range of each pair of blades and the power range. Referring to Table 1, SRi indicates the pitch speed difference range of each pair of blades corresponding to the i-th power range (i.e., the pitch speed difference ranges of blade 1 and blade 2, blade 1 and blade 3, and blade 2 and blade 2 corresponding to the i-th power range are all SRi). When the wind turbine pitches in the i-th power range, if there is no pitch fault, the pitch speed difference of each pair of blades will generally not exceed SRi (e.g., pitch speed difference range [-5 degrees / s, 5 degrees / second]), i=1, 2, 3, 4, 5.

[0044]

[0045] For example, at a certain sampling time, the power data of the wind turbine generator and the pitch speed of the three blades are obtained. If the power is within the first power range, it is calculated whether the pitch speed difference between every two blades exceeds the range SR1.

[0046] As an example, the number of times the pitch speed difference between every two blades in each power range exceeds the corresponding pitch speed difference range can be recorded. For instance, based on the pitch speed of the blades of a wind turbine operating in a certain power range obtained at a certain sampling time, if it is determined that the pitch speed difference between blade 1 and blade 2 exceeds the corresponding pitch speed range, then the number of times the pitch speed difference between blade 1 and blade 2 exceeds the pitch speed difference range corresponding to the certain power range is increased by 1.

[0047] As an example, the mapping relationship is obtained in the following way: according to the power range, the pitch speed of the blades of multiple wind turbine generator sets during pitch operation is divided into data compartments; for any power range, the pitch speed difference between every two blades of each of the multiple wind turbine generator sets is calculated; for any power range, the pitch speed difference range between every two blades corresponding to the arbitrary power range is determined based on the pitch speed difference between every two blades of each wind turbine generator set; wherein, the multiple wind turbine generator sets are of the same type as the wind turbine generator sets.

[0048] As an example, the plurality of wind turbine generator sets may be multiple wind turbine generator sets of the same type as the wind turbine generator set in the same wind farm.

[0049] As an example, the plurality of wind turbine generator sets may include the wind turbine generator sets.

[0050] As an example, pitch speed data from multiple wind turbine generators can be collected through a SCADA system, and then the collected pitch speed data can be processed.

[0051] As an example, the pitch angle data and / or pitch speed data acquired by the SCADA system during pitch control for each wind turbine can be read using the following fields:

[0052] RECTIME = 'rectime' #time POWER = 'WTUR_PwrAt_Ra_F32' #active power

[0053] BLADE_ANGLE1 = 'WTPS_Ang_Ra_F32_blade1' # Pitch angle of blade 1 BLADE_ANGLE2 = 'WTPS_Ang_Ra_F32_blade2' # Pitch angle of blade 2 BLADE_ANGLE3 = 'WTPS_Ang_Ra_F32_blade3' # Pitch angle of blade 3 BLADE_SPEED1 = 'WTPS_Spd_Ra_F32_blade1' # Pitch speed of blade 1 BLADE_SPEED2 = 'WTPS_Spd_Ra_F32_blade2' # Pitch speed of blade 2 BLADE_SPEED3 = 'WTPS_Spd_Ra_F32_blade3' # Pitch speed of blade 3

[0054] As an example, the steps for data partitioning of the pitch speed of blades during the pitch operation of multiple wind turbine generators may include: filtering the acquired pitch speed of blades during the pitch operation of multiple wind turbine generators according to preset rules to remove abnormal or erroneous data, and then partitioning the remaining pitch speed data according to power range.

[0055] As an example, pitch speed data that meets at least one of the following conditions can be identified as pitch speed data that needs to be discarded: the active power corresponding to the pitch speed data is not greater than the rated power. a % (e.g., 60%); pitch speed data is not available. b degrees / second (e.g., -5 degrees / second) to degrees c Within the range of 5 degrees / second (e.g., 5 degrees / second); the difference in pitch speed between the two blades is greater than a preset value (e.g., 3 degrees / second), where, a , b , c This is a preset value, which can be determined based on the fan model.

[0056] As an example, if the number of pitch speed data to be removed for a certain wind turbine is greater than a preset value (e.g., 10), all pitch speed data for that wind turbine can be removed.

[0057] For example, if the pitch speed of three blades of a wind turbine is collected at a certain sampling time, and at least one of the pitch speed differences between any two blades is greater than 3 degrees / second (for example, the pitch speed difference between blade 1 and blade 2 is greater than 3 degrees / second), then the pitch speed data of that set can be discarded.

[0058] For example, if the pitch speed of the three blades of a wind turbine at a certain sampling time exceeds the range of [-5 degrees / second, 5 degrees / second], then the pitch speed data of the wind turbine collected at that sampling time can be discarded.

[0059] For example, if the active power of the wind turbine corresponding to the pitch speed data is less than 60% of the rated power of the wind turbine, then the pitch speed data can be discarded.

[0060] For example, if the pitch speed data of a certain wind turbine is removed beyond the preset number according to the above removal rules, then all the pitch speed data corresponding to that wind turbine will be removed.

[0061] As an example, if it is determined that the pitch speed data of a certain wind turbine has been removed beyond the preset number according to the above-mentioned removal rules, an alarm message indicating that the wind turbine has a fault can be output. For example, the sensor that collects data from the wind turbine may have malfunctioned.

[0062] As an example, for any given power range, the step of determining the range of pitch speed difference between two blades corresponding to the given power range based on the pitch speed difference between two blades of each wind turbine generator set includes: calculating the average value of the pitch speed difference between two blades of each wind turbine generator set; adding a first preset increment to the average value as the upper limit of the range of pitch speed difference between two blades corresponding to the given power range; and subtracting the first preset increment from the average value as the lower limit of the range of pitch speed difference between two blades corresponding to the given power range.

[0063] For ease of description, we will use one day's sampling data from three wind turbine generators in the same wind farm as an example.

[0064] For example, after data is segmented according to power range, for the first power range, the first wind turbine has, for example, 1,000 pitch speed data, the second wind turbine has, for example, 1,000 pitch speed data, and the third wind turbine has, for example, 1,000 data, where each data point indicates the pitch speed data of the three blades of the wind turbine at a certain sampling time.

[0065] For each data point corresponding to the first power range, calculate the pitch speed difference between every two blades, specifically the difference between the pitch speeds of blade 1 and blade 2, blade 1 and blade 3, and blade 2 and blade 3. This yields 9000 differences.

[0066] Then, the average value of the 9000 differences is calculated, and the average value is added to the first preset increment (e.g., 0.15) as the upper limit of the pitch speed difference range between each pair of blades corresponding to the first power range (i.e., the pitch speed difference range between blade 1 and blade 2, the pitch speed difference range between blade 1 and blade 3, and the pitch speed difference range between blade 2 and blade 3). The average value is subtracted from the first preset increment as the lower limit of the pitch speed difference range between each pair of blades corresponding to the first power range.

[0067] Similarly, the range of pitch speed difference between each pair of blades corresponding to other power ranges can be obtained.

[0068] Although the above describes determining the range of pitch speed differences between each pair of blades corresponding to each power range based on the average pitch speed difference between each pair of blades of each wind turbine, this is only an example.

[0069] As an example, the corresponding pitch speed difference range can also be obtained in other ways based on the pitch speed difference between every two blades of each wind turbine.

[0070] For example, the minimum pitch speed difference between every two blades of each wind turbine can be added to an increment to form the lower limit of the corresponding pitch speed difference range, and the maximum pitch speed difference between every two blades of each wind turbine can be subtracted from an increment to form the upper limit of the corresponding pitch speed difference range.

[0071] As an example, the first preset increment could be an empirical value.

[0072] As an example, the first preset increment can be the absolute value of the maximum value among the differences between the 9000 differences and the average value, or the absolute value minus a certain value.

[0073] Return to reference Figure 1 In step S103, when the number of pitch speed differences between two blades that exceed the range of corresponding pitch speed differences is greater than a first preset number (e.g., 3), a first pitch fault warning message indicating that a pitch fault has occurred is output.

[0074] For example, when the number of blades 1 and 2 corresponding to the first power range whose pitch speed difference exceeds the range of the pitch speed difference between blades 1 and 2 corresponding to the first power range exceeds a first preset number, the first pitch fault information indicating that a pitch fault has occurred is output. At this time, the first pitch fault warning information output can be a warning information indicating that blades 1 and 2 may have a pitch fault.

[0075] For example, if the number of times the pitch speed difference between blade 1 and blade 3 corresponding to the second power range exceeds the range of the pitch speed difference between blade 1 and blade 3 corresponding to the second power range exceeds the first preset number, a first pitch fault warning message indicating that a pitch fault has occurred will also be output. At this time, the first pitch fault message can be a warning message indicating that blade 1 and blade 3 may have a fault.

[0076] As an example, the first preset increment and the first preset quantity can be obtained based on big data. For instance, based on the obtained pitch speed data and pitch fault data of multiple wind turbine generators, the pitch speed data before the pitch fault occurred can be determined, and the preset increment and the first preset quantity can be determined according to the distribution pattern of the pitch speed data before the pitch fault occurred. For example, the preset increment and the first preset quantity can be determined with prediction accuracy as the optimization objective.

[0077] Figure 2 The graph shows the pitch speed data of multiple wind turbine generators in a wind farm during the pitch control period.

[0078] Reference Figure 2 The horizontal axis represents the power of the wind turbine generator set, and the vertical axis represents the pitch speed difference between every two blades of each wind turbine generator set. Figure 2The numerous dots represent the pitch speed difference between every two blades of a wind turbine generator set, while the solid line represents the pitch speed difference data for a specific turbine generator set. Figure 2 As can be seen, the pitch speed difference between every two blades of most wind turbine generators without pitch faults is around 0 degrees / second (located between the two dotted lines in the figure), and the average pitch speed difference is close to 0 degrees / second. However, the pitch speed difference between blade 1 and the other two blades of the problematic unit reached 0.2 degrees / second. Moreover, compared with the healthy units, the pitch speed difference data of the problematic unit deviated far from 0 degrees / second and the deviation was greater than 0.15 degrees / second. After shutdown, boarding the aircraft confirmed that the electromagnetic brake of the pitch motor of blade 1 was completely stuck.

[0079] For example, the first preset increment corresponding to a certain power range can be set to, for example, 0.15 degrees / s (<0.2 degrees / s), and the first preset quantity can be set to, for example, 3. In this way, when the electromagnetic brake of the wind turbine generator does not report a fault or is not completely damaged, a warning message can be output to remind the user to maintain the relevant components in a timely manner.

[0080] Figure 3 A flowchart of a pitch fault prediction method for a wind turbine generator set according to another embodiment of the present disclosure is shown.

[0081] Reference Figure 3 In step S301, during the pitch operation of the wind turbine generator set, the pitch angle of each blade of the wind turbine generator set and the active power of the wind turbine generator set are acquired at each sampling time.

[0082] The above describes the sampling method for the pitch speed of wind turbine blades during pitch control. The blade pitch angle during pitch control can be obtained in a similar way, so it will not be repeated here.

[0083] In step S302, the power range of the active power of the wind turbine generator at each sampling time is determined, and based on the mapping relationship between the pitch angle difference range of each pair of blades and the power range, it is determined whether the pitch angle difference of each pair of blades at each sampling time exceeds the corresponding pitch angle difference range.

[0084] The method of dividing the power range can be compared with the reference. Figure 1 The power ranges described are divided in the same or similar ways.

[0085] As an example, the mapping relationship between the pitch angle difference range of each pair of blades and the power range can be stored in the form of a mapping table.

[0086] Table 2 shows an example of the mapping relationship between the pitch angle difference range of each pair of blades and the power range. Referring to Table 2, ARi indicates the pitch angle difference range of each pair of blades corresponding to the i-th power range (i.e., the pitch angle difference ranges of blades 1 and 2, blades 1 and 3, and blades 2 and 3 corresponding to the i-th power range are all ARi). When the wind turbine pitches in the i-th power range, if there is no pitch fault, the pitch angle difference of each pair of blades during the pitching period will generally not exceed ARi, i=1, 2, 3, 4, 5.

[0087]

[0088] For example, at a certain sampling time, the power data of the wind turbine generator and the pitch angle of the three blades are obtained. If the power belongs to the first power range, it is calculated whether the pitch angle difference between every two blades exceeds the range AR1.

[0089] As an example, the mapping relationship between the pitch angle difference range and the power range is obtained in the following way: according to the power range, the pitch angle of the blades of multiple wind turbine generator sets during pitch operation is divided into data compartments; for any power range, the pitch angle difference between every two blades of each of the multiple wind turbine generator sets is calculated; for any power range, the pitch angle difference range between every two blades corresponding to the arbitrary power range is determined based on the pitch angle difference between every two blades of each wind turbine generator set.

[0090] As an example, the number of times the pitch angle difference between every two blades exceeds the corresponding pitch angle difference range for each power range can be recorded. For instance, based on the pitch angle of the blades of a wind turbine operating in a certain power range obtained at a certain sampling time, if it is determined that the pitch angle difference between blade 1 and blade 2 exceeds the corresponding pitch angle difference range, then the number of times the pitch angle difference between blade 1 and blade 2 exceeds the pitch angle difference range corresponding to the certain power range is increased by 1.

[0091] As an example, pitch angle data during the pitch adjustment of multiple wind turbine generators can be collected through a SCADA system, and the collected pitch angle data can be processed.

[0092] As an example, the plurality of wind turbine generator sets may be multiple wind turbine generator sets of the same type in the same wind farm as the wind turbine generator sets.

[0093] As an example, the steps for data compartmenting of blade pitch angles during pitch control operations of multiple wind turbine generators may include: filtering the acquired blade pitch angles during pitch control operations of multiple wind turbine generators according to preset rules to remove abnormal or erroneous data, and then compartmenting the remaining pitch angle data according to power range.

[0094] As an example, pitch angle data that meets at least one of the following conditions can be identified as pitch angle data that needs to be discarded: the active power corresponding to the pitch angle data is not greater than the rated power. d % (e.g., 20%); the blade pitch angle is not... e (For example, -5) degrees to f (For example, between 100) degrees; the pitch angle difference between the two blades is greater than a preset value (for example, 3 degrees), where, d , e , f This is a preset value, which can be determined based on the fan model.

[0095] As an example, if the number of pitch angle data to be removed for a certain wind turbine is greater than a preset value (e.g., 10), all pitch angle data for that wind turbine can be removed.

[0096] For example, for the pitch angles of three blades of a wind turbine during pitch control at a certain sampling time, if at least one of the pitch angle differences between any two blades is greater than 3 degrees (for example, the difference between the pitch angles of blade 1 and blade 2 is greater than 3 degrees), then the set of pitch angle data can be discarded.

[0097] For example, if at a certain sampling time, there is a pitch angle in the three blades of a wind turbine that exceeds the range of -5 degrees to 100 degrees, then the pitch angle data of the wind turbine collected at that sampling time can be discarded.

[0098] For example, if the active power of the wind turbine corresponding to the pitch angle data is less than 20% of the rated power, then the pitch angle data can be discarded.

[0099] For example, if the pitch angle data of a certain wind turbine is removed beyond the preset number according to the above removal rules, then all the pitch angle data corresponding to that wind turbine will be removed.

[0100] As an example, if it is determined that the pitch angle data of a certain wind turbine has been removed beyond the preset number according to the above-mentioned removal rules, an alarm message indicating that the wind turbine has a fault can be output. For example, the sensor that collects data from the wind turbine may have malfunctioned.

[0101] As an example, for any given power range, the step of determining the pitch angle range corresponding to the given power range based on the pitch angle difference between every two blades of each wind turbine generator set includes: calculating the average value of the pitch angle difference between every two blades of each wind turbine generator set; adding a second preset increment to the average value as the upper limit of the pitch angle difference range between every two blades corresponding to the given power range; and subtracting the second preset increment from the average value as the lower limit of the pitch angle difference range between every two blades corresponding to the given power range.

[0102] For ease of description, we will use the pitch angle data collected from three wind turbine generators in the same wind farm over one day as an example.

[0103] For example, after dividing the pitch angle data into compartments according to the power range, for the first power range, the first wind turbine has 1,000 pitch angle data, the second wind turbine has 1,000 pitch angle data, and the third wind turbine has 1,000 pitch angle data. Each pitch angle data indicates the pitch angle data of the three blades of the wind turbine at a certain sampling time.

[0104] For each pitch angle data corresponding to the first power range, calculate the difference in pitch angle between every two blades, that is, calculate the pitch angle difference between blade 1 and blade 2, the pitch angle difference between blade 1 and blade 3, and the pitch angle difference between blade 2 and blade 3. This yields 9000 differences.

[0105] Then, the average value of the 9000 difference is calculated, and the average value is added to the second preset increment as the upper limit of the pitch angle difference range of each pair of blades corresponding to the first power range (i.e. the pitch angle difference range between blade 1 and blade 2, the pitch angle difference range between blade 1 and blade 3, and the sum of the pitch angle difference ranges between blade 2 and blade 3). The average value is subtracted from the second preset increment (e.g., 0.15) as the lower limit of the pitch angle difference range of each pair of blades corresponding to the first power range.

[0106] Similarly, the pitch angle difference range for each pair of blades corresponding to other power ranges can be obtained.

[0107] Although the above describes determining the range of pitch angle differences between each pair of blades corresponding to each power range based on the average pitch angle difference between each pair of blades of each wind turbine, this is only an example.

[0108] As an example, the corresponding pitch angle difference range can also be obtained in other ways based on the pitch angle difference between every two blades of each wind turbine.

[0109] For example, the minimum pitch angle difference between every two blades of each wind turbine can be added to an increment to form the lower limit of the corresponding pitch angle difference range, and the maximum pitch angle difference between every two blades of each wind turbine can be subtracted from an increment to form the upper limit of the corresponding pitch angle difference range.

[0110] As an example, the second preset increment could be an empirical value.

[0111] As an example, the second preset increment can be the absolute value of the maximum value among the differences between the 9000 differences and the average value minus a certain value.

[0112] Return to reference Figure 3 In step S303, when the number of pitch angle differences between any two blades that exceed the corresponding pitch angle difference range is greater than the second preset number, a second pitch fault warning message indicating a pitch fault is output.

[0113] For example, when the number of pitch speed differences between two blades that exceed the corresponding pitch speed difference range is greater than a second preset number (e.g., 3), a second pitch fault warning message indicating a pitch fault is output.

[0114] For example, during pitch control in the first power range of a wind turbine generator, if the number of times the pitch speed difference between blade 1 and blade 2 exceeds the range corresponding to the pitch speed difference between blade 1 and blade 2 in the first power range exceeds a second preset number, then a second pitch fault message indicating a pitch fault will be output. As an example, the output second pitch fault message could be a warning message indicating a possible pitch fault in blade 1 and blade 2. This allows the user to easily determine which two blades to inspect.

[0115] As an example, the second preset increment and the second preset quantity can be obtained based on big data. For instance, based on the obtained pitch angle data during pitch control of multiple wind turbine generators and pitch fault data, the pitch angle data during the pitch control period before the pitch fault occurred can be determined, and the second preset increment and the second preset quantity can be determined according to the distribution pattern of the pitch angle data before the pitch fault occurred. For example, the second preset increment and the second preset quantity can be determined based on a large amount of pitch angle data during the pitch control period before the pitch fault occurred, with the accuracy of pitch fault prediction as the optimization objective.

[0116] Figure 4 It is a graph showing the pitch angle data of multiple wind turbine generators in a certain wind farm during pitch control.

[0117] Reference Figure 4The horizontal axis represents the power of the wind turbine generator, and the vertical axis represents the pitch angle difference between two blades during pitch control. Numerous points in the graph represent the pitch angle difference data between two blades, and the solid line represents the pitch angle difference data of a specific turbine generator. Figure 4 As can be seen, the pitch angle difference between each pair of blades of most wind turbine generators without pitch faults is around 0 degrees (located between the two dotted lines in the figure), and the average pitch angle difference is close to 0 degrees and does not exceed the range of -0.5 degrees to 0.5 degrees. However, the pitch angle difference between blade 3 and the other two blades of the problematic generator reached -0.75 degrees, and many pitch angle difference data of the problematic generator deviated far from 0 degrees and deviated more than 0.5 degrees. After shutdown, it was confirmed by boarding the aircraft that the toothed belt of blade 3 had become loose.

[0118] Therefore, the second preset increment can be set to, for example, 0.5 degrees (<0.75 degrees), and the second preset quantity can be set to, for example, 3. In this way, when the toothed belt of the wind turbine blade becomes loose but no fault is reported, early warning information can be output as soon as possible to remind the user to maintain the relevant components in a timely manner.

[0119] As an example, pitch failures can be predicted based on both pitch speed data and pitch angle data during wind turbine pitch control. Figure 1 and Figure 3 The methods shown are combined to predict pitch faults in wind turbine generators.

[0120] As an example, a pitch fault prediction method for a wind turbine generator set is provided. The pitch fault prediction method includes: during the pitch operation of the wind turbine generator set, acquiring the pitch speed of each blade of the wind turbine generator set and the active power of the wind turbine generator set at each sampling time.

[0121] The method further includes: determining the power range of the active power of the wind turbine generator set at each sampling time; determining whether the pitch speed difference between two blades at each sampling time exceeds the corresponding pitch speed difference range based on the mapping relationship between the pitch speed difference range between two blades and the power range; and outputting a first pitch fault warning message indicating a pitch fault when the number of pitch speed differences between two blades exceeding the corresponding pitch speed difference range is greater than a first preset number.

[0122] According to existing pitch fault detection methods, when the pitch angle difference exceeds a threshold, a pitch fault alarm is output. However, by this time, the pitch fault has already occurred, for example, the toothed belt is severely loose or has detached, or the electromagnetic brake is completely stuck. In contrast, according to the embodiments of this application, since toothed belt detachment and complete electromagnetic brake sticking are gradual faults, pitch faults can be predicted based on pitch speed data and / or pitch angle data during pitch control. An early warning message can be issued before the toothed belt detaches or the electromagnetic brake is completely stuck, thus reducing losses caused by pitch faults.

[0123] Reference above Figures 1 to 4 A method for predicting pitch faults in wind turbine generators according to embodiments of the present disclosure has been described below, with reference to... Figure 5 A pitch fault prediction device for a wind turbine generator set according to an embodiment of the present disclosure is described.

[0124] Figure 5 This is a diagram illustrating the structure of a pitch fault prediction device 500 for a wind turbine generator set according to an embodiment of the present disclosure.

[0125] Reference Figure 5 The pitch fault prediction device 500 may include a data acquisition unit 501, a determination unit 502, and an output unit 503. Those skilled in the art will understand that the pitch fault prediction device 500 may also include other components, and at least one of the components included in the pitch fault prediction device 500 may be omitted, combined, or separated.

[0126] As an example, the acquisition unit 501 may be configured to acquire the pitch speed of each blade of the wind turbine and the active power of the wind turbine at each sampling time during the pitch operation of the wind turbine.

[0127] As an example, the determining unit 502 can be configured to: determine the power range in which the active power of the wind turbine generator is located at each sampling time, and determine whether the pitch speed difference between each pair of blades exceeds the corresponding pitch speed difference range based on the mapping relationship between the pitch speed difference range between each pair of blades and the power range.

[0128] As an example, the output unit 503 can be configured to output a first pitch fault warning message indicating that a pitch fault has occurred when the number of pitch speed differences between two blades that exceed the corresponding pitch speed difference range is greater than a first preset number.

[0129] As an example, the acquisition unit 501 can also be configured to acquire the pitch angle of each blade of the wind turbine and the active power of the wind turbine at each sampling time during the pitch operation of the wind turbine.

[0130] As an example, the determining unit 502 can also be configured to: determine the power range in which the active power of the wind turbine generator is located at each sampling time, and determine whether the pitch angle difference between each pair of blades exceeds the corresponding pitch angle difference range based on the mapping relationship between the pitch angle difference range between each pair of blades and the power range.

[0131] As an example, the output unit 503 can also be configured to output a second pitch fault warning message indicating that a pitch fault has occurred when the number of pitch angle differences between two blades exceeds the corresponding pitch angle difference range is greater than a second preset number.

[0132] According to embodiments of this disclosure, a computer-readable storage medium storing instructions may also be provided, wherein when the instructions are executed by at least one processor, they cause at least one processor to perform a pitch fault prediction method for a wind turbine generator according to embodiments of this disclosure. Examples of computer-readable storage media herein include: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disc storage, hard disk drive (HDD), solid-state drive (SSD), card storage (such as multimedia cards, secure digital (SD) cards, or ultra-fast digital (XD) cards), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, and any other device configured to store a computer program and any associated data, data files, and data structures in a non-transitory manner and to provide the computer program and any associated data, data files, and data structures to a processor or computer so that the processor or computer can execute the computer program. The computer program in the aforementioned computer-readable storage medium can run in an environment deployed in computer devices such as clients, hosts, agent devices, servers, etc. Furthermore, in one example, the computer program and any associated data, data files, and data structures are distributed across a networked computer system, such that the computer program and any associated data, data files, and data structures are stored, accessed, and executed in a distributed manner through one or more processors or computers.

[0133] According to embodiments of this disclosure, a controller may also be provided, which may include a processor and a memory. The memory stores a computer program that, when executed by the processor, implements the pitch fault prediction method for wind turbine generators as described above.

[0134] According to embodiments of this disclosure, a computer program product may also be provided, wherein the instructions in the computer program product are executable by a processor of a computer device to perform the pitch fault prediction method for wind turbine generators described herein.

[0135] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

Claims

1. A method for predicting pitch faults in wind turbine generator sets, characterized in that, The pitch fault prediction method includes: During the pitch operation of the wind turbine generator set, the pitch speed of each blade of the wind turbine generator set and the active power of the wind turbine generator set are acquired at each sampling time. Determine the power range of the active power of the wind turbine generator at each sampling time, and based on the mapping relationship between the pitch speed difference range of every two blades and the power range, determine whether the pitch speed difference of every two blades at each sampling time exceeds the corresponding pitch speed difference range; and When the number of pitch speed differences between any two blades that exceed the corresponding pitch speed difference range is greater than a first preset number, a first pitch fault warning message indicating a pitch fault is output.

2. The pitch fault prediction method as described in claim 1, characterized in that, The mapping relationship is obtained in the following way: Data on the blade pitch speed during pitch control operations of multiple wind turbine generators is divided into compartments according to power range. For any given power range, calculate the pitch speed difference between every two blades of each of the plurality of wind turbine generator sets. For any given power range, the range of pitch speed difference between every two blades corresponding to that power range is determined based on the pitch speed difference between every two blades of each wind turbine generator. The plurality of wind turbine generator sets are of the same type as the wind turbine generator sets.

3. The pitch fault prediction method as described in claim 2, characterized in that, For any given power range, the step of determining the range of pitch speed differences between every two blades corresponding to that power range, based on the pitch speed difference between every two blades of each wind turbine generator, includes: Calculate the average pitch speed difference between every two blades of each wind turbine generator set; The average value plus a first preset increment is used as the upper limit of the pitch speed difference range between every two blades corresponding to any given power range, and the average value minus the first preset increment is used as the lower limit of the pitch speed difference range between every two blades corresponding to any given power range.

4. A method for predicting pitch faults in wind turbine generator sets, characterized in that, The pitch fault prediction method includes: During the pitch operation of the wind turbine generator set, the pitch angle of each blade of the wind turbine generator set and the active power of the wind turbine generator set are acquired at each sampling time. Determine the power range of the wind turbine generator's active power at each sampling time, and based on the mapping relationship between the pitch angle difference range of each pair of blades and the power range, determine whether the pitch angle difference between each pair of blades at each sampling time exceeds the corresponding pitch angle difference range; and When the number of pitch angle differences between any two blades that exceed the corresponding pitch angle difference range is greater than the second preset number, a second pitch fault warning message indicating a pitch fault will be output.

5. The pitch fault prediction method as described in claim 4, characterized in that, The mapping relationship between the pitch angle difference range and the power range is obtained in the following way: Data on blade pitch angles during pitch control operations of multiple wind turbine generators are divided into compartments according to power range. For any given power range, calculate the pitch angle difference between every two blades of each of the plurality of wind turbine generator sets. For any given power range, the pitch angle difference range of each pair of blades corresponding to that power range is determined based on the pitch angle difference between each pair of blades of each wind turbine generator set.

6. The pitch fault prediction method as described in claim 5, characterized in that, For any given power range, the step of determining the pitch angle range corresponding to that power range based on the pitch angle difference between every two blades of each wind turbine generator includes: Calculate the average pitch angle difference between every two blades of each wind turbine generator set; The average value plus the second preset increment is used as the upper limit of the pitch angle difference range between each pair of blades corresponding to any power range, and the average value minus the second preset increment is used as the lower limit of the pitch angle difference range between each pair of blades corresponding to any power range.

7. A pitch fault prediction device for wind turbine generator sets, characterized in that, The pitch fault prediction device includes: The acquisition unit is configured to acquire the pitch speed of each blade of the wind turbine and the active power of the wind turbine at each sampling time during the pitch operation of the wind turbine. The determining unit is configured to: determine the power range in which the active power of the wind turbine generator falls at each sampling time, and, based on the mapping relationship between the pitch speed difference range of every two blades and the power range, determine whether the pitch speed difference between every two blades at each sampling time exceeds the corresponding pitch speed difference range; and The output unit is configured to output a first pitch fault warning message indicating a pitch fault when the number of pitch speed differences between two blades that exceed the corresponding pitch speed difference range is greater than a first preset number.

8. A pitch fault prediction device for wind turbine generator sets, characterized in that, The pitch fault prediction device includes: The acquisition unit is configured to acquire the pitch angle of each blade of the wind turbine and the active power of the wind turbine at each sampling time during the pitch operation of the wind turbine. The determining unit is configured to: determine the power range in which the active power of the wind turbine generator falls at each sampling time, and, based on the mapping relationship between the pitch angle difference range of each pair of blades and the power range, determine whether the pitch angle difference between each pair of blades at each sampling time exceeds the corresponding pitch angle difference range; and The output unit is configured to output a second pitch fault warning message indicating a pitch fault when the number of pitch angle differences between any two blades exceeds the corresponding pitch angle difference range is greater than a second preset number.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the pitch fault prediction method for wind turbine generator sets as described in any one of claims 1 to 6.

10. A controller, characterized in that, The controller includes: processor; and A memory storing a computer program that, when executed by a processor, implements the pitch fault prediction method for wind turbine generator sets as described in any one of claims 1 to 6.

Images