A fault detection method, apparatus, electronic device, and storage medium

Abstract

This application provides a fault detection method, device, electronic device, and storage medium, relating to the field of wind turbine generator condition monitoring technology. The method includes: when the wind turbine is in power generation operation mode, acquiring a first electrical signal from the wind turbine; performing frequency domain analysis on the first electrical signal to obtain a first power spectral density; if a fault characteristic frequency component of the wind turbine's main bearing is present in the first power spectral density, switching the wind turbine to an off-grid, no-load mode; and acquiring a second electrical signal from the wind turbine; performing frequency domain analysis on the second electrical signal to obtain a second power spectral density; if a fault characteristic frequency component of the wind turbine's main bearing is present in the second power spectral density, determining that the wind turbine's main bearing has failed. Determining whether the wind turbine's main bearing has a fault based on two modes can improve the accuracy of diagnosis.

Description

Technical Field

[0001] This application relates to the field of wind turbine generator condition monitoring technology, and more specifically, to a fault detection method, device, electronic equipment, and storage medium. Background Technology

[0002] Existing methods for diagnosing main bearing faults in wind turbines typically involve performing frequency domain analysis on the vibration signal of the main bearing to obtain the frequency composition of the vibration signal, and then comparing and analyzing it with the fault characteristic frequency to achieve the purpose of diagnosing the main bearing fault.

[0003] Existing methods for diagnosing wind turbine main bearing faults require the installation of additional vibration sensors on the main bearing, increasing the cost of the diagnostic approach. Furthermore, the large size of the main bearing causes the collected vibration signal to couple with information from many transmission paths, resulting in a low signal-to-noise ratio and increasing the difficulty of signal processing. Additionally, wind turbine main bearings typically operate under low-speed, heavy-load conditions, where the fault signals contained in the vibration signal are weak and subtle, easily affected by environmental noise, leading to indistinct fault characteristic frequencies and making accurate diagnosis of main bearing faults difficult. Summary of the Invention

[0004] The purpose of this application is to provide a fault detection method, device, electronic equipment, and storage medium that can improve the accuracy of fault detection of wind turbine main bearings.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows:

[0006] In a first aspect, embodiments of this application provide a fault detection method, the method comprising:

[0007] When the wind turbine is in power generation mode, the first electrical signal of the wind turbine is collected.

[0008] Frequency domain analysis is performed on the first electrical signal to obtain the first power spectral density of the first electrical signal;

[0009] When the wind turbine main bearing fault characteristic frequency component exists in the first power spectral density, the wind turbine is switched to off-grid no-load mode, and the second electrical signal of the wind turbine is collected.

[0010] Frequency domain analysis of the second electrical signal yields the second power spectral density of the second electrical signal;

[0011] When the main bearing fault characteristic frequency component of the wind turbine is present in the second power spectral density, it is determined that the main bearing of the wind turbine has failed.

[0012] In an optional implementation, the step of performing frequency domain analysis on the first electrical signal to obtain the first power spectral density of the first electrical signal includes:

[0013] The first electrical signal is segmented to obtain multiple segmented electrical signals;

[0014] The frequency domain amplitude of the first electrical signal is obtained by sequentially performing Fourier transform on the multiple segmented electrical signals.

[0015] Calculate the mean square value of the frequency domain amplitude;

[0016] Determine the ratio of the mean square value to the frequency resolution;

[0017] The ratio is converted into a single-sided spectrum to obtain the first power spectral density of the first electrical signal.

[0018] In an optional implementation, the step of converting the ratio into a one-sided spectrum to obtain the first power spectral density of the first electrical signal includes:

[0019] Determine the proportional value in the ratio;

[0020] Multiplying the proportional value by a preset value yields the first power spectral density of the first electrical signal.

[0021] In an optional implementation, the step of switching the wind turbine to off-grid no-load mode and collecting the second electrical signal of the wind turbine when the first power spectral density contains a characteristic frequency component of the wind turbine main bearing fault includes:

[0022] Determine the first amplitude of each peak in the first power spectral density;

[0023] Determine the minimum and maximum amplitude values ​​among the first amplitude values;

[0024] Calculate the product of the minimum amplitude and the preset multiple;

[0025] When the maximum amplitude value is greater than the product, the frequency corresponding to the maximum amplitude value is determined;

[0026] The frequency is matched with the characteristic frequencies of each component of the wind turbine.

[0027] If the frequency matches the characteristic frequency of any component of the wind turbine, it is determined that the first power spectral density contains a wind turbine main bearing fault characteristic frequency component.

[0028] The wind turbine is switched to off-grid no-load mode, and the second electrical signal of the wind turbine is collected.

[0029] In an optional embodiment, the wind turbine includes an outer ring component, an inner ring component, a rolling element component, a first cage component, and a second cage component;

[0030] The characteristic frequency of the outer ring component satisfies the following formula:

[0031]

[0032] The characteristic frequency of the inner ring component satisfies the following formula:

[0033]

[0034] The characteristic frequency of the rolling element component satisfies the following formula:

[0035]

[0036] The characteristic frequency of the first cage component satisfies the following formula:

[0037]

[0038] The characteristic frequency of the second cage component satisfies the following formula:

[0039]

[0040] Where Z is the number of rolling elements, d is the diameter of the rolling elements, D is the pitch diameter of the main bearing, α is the contact angle of the main bearing, and f is the contact angle of the main bearing. r The rotational frequency of the main bearing.

[0041] In an optional implementation, the step of segmenting the first electrical signal to obtain multiple segmented electrical signals includes:

[0042] The first electrical signal is segmented through a Hamming window to obtain multiple segmented electrical signals.

[0043] In an optional implementation, after the step of identifying the characteristic frequency components of wind turbine main bearing failure in the first power spectral density, the method further includes:

[0044] Output a warning signal for a fault in the main bearing of the wind turbine.

[0045] Secondly, embodiments of this application provide a fault detection device, the device comprising:

[0046] The first acquisition module is used to acquire the first electrical signal of the wind turbine when the wind turbine is in power generation operation mode;

[0047] The first analysis module is used to perform frequency domain analysis on the first electrical signal to obtain the first power spectral density of the first electrical signal.

[0048] The second acquisition module is used to switch the wind turbine to off-grid no-load mode and acquire the second electrical signal of the wind turbine when the main bearing fault characteristic frequency component of the wind turbine is present in the first power spectral density.

[0049] The second analysis module is used to perform frequency domain analysis on the second electrical signal to obtain the second power spectral density of the second electrical signal;

[0050] The determination module is used to determine that the main bearing of the wind turbine has failed when the main bearing failure characteristic frequency component of the wind turbine is present in the second power spectral density.

[0051] Thirdly, embodiments of this application provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the fault detection method.

[0052] Fourthly, embodiments of this application provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the fault detection method.

[0053] This application has the following beneficial effects:

[0054] This application determines whether the main bearing of a wind turbine is faulty in the power generation operation mode by performing frequency domain analysis on the first electrical signal of the wind turbine. If a fault component is found in the main bearing during power generation operation, the application further improves the accuracy of the diagnosis by switching the wind turbine to an off-grid, no-load mode and acquiring a second electrical signal in this mode. Frequency domain analysis of this second signal yields a second power spectral density, which is then used to determine whether the main bearing is also faulty in the off-grid, no-load mode. If so, the application confirms a fault in the main bearing. Determining the presence of a fault in the main bearing based on two modes improves diagnostic accuracy. Furthermore, this application eliminates the need for additional vibration sensors by collecting and analyzing the wind turbine's electrical signals, reducing diagnostic costs. The high signal-to-noise ratio of the collected electrical signals also simplifies signal processing. Attached Figure Description

[0055] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 A block diagram illustrating an electronic device provided in an embodiment of this application;

[0057] Figure 2 This is one of the flowcharts illustrating a fault detection method provided in an embodiment of this application;

[0058] Figure 3 This is a second schematic flowchart of a fault detection method provided in an embodiment of this application;

[0059] Figure 4 The third schematic flowchart of a fault detection method provided in this application embodiment;

[0060] Figure 5 This is a schematic diagram of the first power spectral density of the first electrical signal provided in an embodiment of this application;

[0061] Figure 6 This is a structural block diagram of a fault detection device provided in an embodiment of this application. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0063] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0064] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0065] In the description of this application, it should be noted that if terms such as "upper," "lower," "inner," or "outer" are used to indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of the invention is usually placed during use, they are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0066] Furthermore, the terms "first" and "second" are used only to distinguish descriptions and should not be interpreted as indicating or implying relative importance.

[0067] In the description of this application, it should also be noted that, unless otherwise expressly specified and limited, the terms "set up," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0068] Through extensive research, the inventors discovered that existing methods for diagnosing main bearing faults in wind turbines typically involve frequency domain analysis of the main bearing's vibration signal to obtain the frequency composition of the vibration signal, and then comparing and analyzing this composition with the fault characteristic frequency to achieve the purpose of diagnosing the main bearing fault.

[0069] Existing methods for diagnosing wind turbine main bearing faults require the installation of additional vibration sensors on the main bearing, increasing the cost of the diagnostic approach. Furthermore, the large size of the main bearing causes the collected vibration signal to couple with information from many transmission paths, resulting in a low signal-to-noise ratio and increasing the difficulty of signal processing. Additionally, wind turbine main bearings typically operate under low-speed, heavy-load conditions, where the fault signals contained in the vibration signal are weak and subtle, easily affected by environmental noise, leading to indistinct fault characteristic frequencies and making accurate diagnosis of main bearing faults difficult.

[0070] In view of the above-mentioned problems, this embodiment provides a fault detection method, device, electronic device and storage medium, which can determine whether there is a fault in the main bearing of the wind turbine based on two modes, thereby improving the accuracy of diagnosis. Furthermore, this application analyzes the electrical signals of the wind turbine without the need to install additional vibration sensors, reducing the cost of diagnosis. The acquired electrical signals have a high signal-to-noise ratio, which reduces the difficulty of signal processing. The solution provided in this embodiment will be described in detail below.

[0071] This embodiment provides an electronic device capable of detecting faults in the main bearing of a wind turbine. In one possible implementation, the electronic device can be a user terminal, such as, but not limited to, a server, smartphone, personal computer (PC), tablet computer, personal digital assistant (PDA), mobile internet device (MID), etc.

[0072] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the structure of the electronic device 100 provided in the embodiments of this application. The electronic device 100 may further include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown. Figure 1 The components shown can be implemented using hardware, software, or a combination thereof.

[0073] The electronic device 100 includes a fault detection device 110, a memory 120, and a processor 130.

[0074] The components of the memory 120 and processor 130 are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines. The fault detection device 110 includes at least one software function module that can be stored in the memory 120 in the form of software or firmware or embedded in the operating system (OS) of the electronic device 100. The processor 130 is used to execute executable modules stored in the memory 120, such as the software function modules and computer programs included in the fault detection device 110.

[0075] The memory 120 may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory 120 is used to store programs, and the processor 130 executes the programs after receiving execution instructions.

[0076] Please refer to Figure 2 , Figure 2 For application Figure 1 The flowchart below shows a fault detection method for an electronic device 100, and the method includes a detailed description of each step.

[0077] Step 201: When the wind turbine is in power generation mode, collect the first electrical signal of the wind turbine.

[0078] Step 202: Perform frequency domain analysis on the first electrical signal to obtain the first power spectral density of the first electrical signal.

[0079] Step 203: When the main bearing fault characteristic frequency component of the wind turbine is present in the first power spectral density, switch the wind turbine to off-grid no-load mode and collect the second electrical signal of the wind turbine.

[0080] Step 204: Perform frequency domain analysis on the second electrical signal to obtain the second power spectral density of the second electrical signal.

[0081] Step 205: When the main bearing fault characteristic frequency component of the wind turbine is present in the second power spectral density, it is determined that the main bearing of the wind turbine has failed.

[0082] In one example, it is determined whether the wind turbine is in power generation mode. If the wind turbine is in power generation mode, the first electrical signal of the wind turbine is collected at a certain sampling frequency within a set sampling time period. If the wind turbine is not in power generation mode, the wind turbine's operating status is monitored again until the wind turbine is detected to be in power generation mode, at which point the first electrical signal of the wind turbine is collected.

[0083] It should be noted that the first electrical signal may include: the active power output of the wind turbine generator, stator current, and voltage of each phase.

[0084] There are various ways to process the first electrical signal. In one example, frequency domain analysis is performed on the first electrical signal to determine whether there are characteristic frequency components of wind turbine main bearing faults in the first power spectral density corresponding to the first electrical signal. If characteristic frequency components of wind turbine main bearing faults are found in the first power spectral density corresponding to the first electrical signal, the wind turbine is switched from the power generation operation mode to the off-grid no-load mode, and the second electrical signal of the wind turbine in the off-grid no-load mode is collected.

[0085] There are several ways to collect the second electrical signal of a wind turbine in off-grid no-load mode. In one example, the second electrical signal of the wind turbine is collected at a certain sampling frequency within a set sampling time period.

[0086] It should be noted that the wind turbine in power generation mode is the mode in which the wind turbine is connected to the public power grid, household power grid, and solar power generation. The wind turbine in off-grid no-load mode is the mode in which the wind turbine is disconnected from the power grid and operates at a low speed. In this mode, the wind turbine does not generate electricity, but it still outputs voltage. In off-grid no-load mode, the hub speed of the wind turbine is controlled below 6 rpm.

[0087] Frequency domain analysis is performed on the second electrical signal collected when the wind turbine is in off-grid no-load mode to obtain the second power spectral density of the second electrical signal. Simultaneously, it is determined whether the second power spectral density of the second electrical signal contains a frequency component characteristic of the wind turbine's main bearing failure. If this frequency component is present in the second power spectral density, then a failure in the wind turbine's main bearing is confirmed. In other words, if both the first power spectral density of the first electrical signal (when the wind turbine is in power generation mode) and the second power spectral density of the second electrical signal (when the wind turbine is in off-grid no-load mode) contain a frequency component characteristic of the wind turbine's main bearing failure, then a failure in the wind turbine's main bearing is confirmed.

[0088] When the first power spectral density of the first electrical signal when the wind turbine is in power generation mode contains a characteristic frequency component of the main bearing failure of the wind turbine, or when the second power spectral density of the second electrical signal when the wind turbine is in off-grid no-load mode contains a characteristic frequency component of the main bearing failure of the wind turbine, it is determined that the main bearing of the wind turbine may have a failure risk.

[0089] It should be noted that the characteristic frequency components of a wind turbine main bearing failure may include: the characteristic frequencies of the outer ring components, the inner ring components, the rolling element components, the first cage component, and the second cage component. Specifically, the characteristic frequency of the first cage component is the frequency at which the cage passes through the outer ring components, and the characteristic frequency of the second cage component is the frequency at which the cage passes through the inner ring components.

[0090] This application determines whether the main bearing of a wind turbine is faulty in the power generation operation mode by performing frequency domain analysis on the first electrical signal of the wind turbine. If a fault component is found in the main bearing during power generation operation, the application further improves the accuracy of the diagnosis by switching the wind turbine to an off-grid, no-load mode and acquiring a second electrical signal in this mode. Frequency domain analysis of this second signal yields a second power spectral density, which is then used to determine whether the main bearing is also faulty in the off-grid, no-load mode. If so, the application confirms a fault in the main bearing. Determining the presence of a fault in the main bearing based on two modes improves diagnostic accuracy. Furthermore, this application eliminates the need for additional vibration sensors by collecting and analyzing the wind turbine's electrical signals, reducing diagnostic costs. The high signal-to-noise ratio of the collected electrical signals also simplifies signal processing.

[0091] There are several ways to perform frequency domain analysis on the first electrical signal to obtain its first power spectral density. In one example, referring to... Figure 3 Here is a flowchart of the steps of the fault detection method provided in this application embodiment, including:

[0092] Step 202-1: Divide the first electrical signal into segments to obtain multiple segmented electrical signals.

[0093] Step 202-2: Perform Fourier transform on multiple segmented electrical signals in sequence to obtain the frequency domain amplitude of the first electrical signal.

[0094] Step 202-3: Calculate the mean square value of the frequency domain amplitude.

[0095] Step 202-4: Determine the ratio of the mean square value to the frequency resolution.

[0096] Step 202-5: Convert the ratio into a single-sided spectrum to obtain the first power spectral density of the first electrical signal.

[0097] There are several ways to segment the first electrical signal. In one example, a Hamming window is used to segment the acquired first electrical signal. It should be noted that the Hamming window width can be set to 256 data points, and the window shift width can be set to 50% of the window width, i.e., 128 data points. These 128 data points are treated as a single segmented electrical signal, and the first electrical signal is processed into multiple segmented electrical signals based on the Hamming window.

[0098] The windowed segmented electrical signals are sequentially subjected to Fast Fourier Transform to obtain the frequency domain amplitude of the first electrical signal, and the first power spectral density of the first electrical signal is calculated based on the frequency domain amplitude of the first electrical signal.

[0099] It should be noted that the ratio of the mean square value of the frequency domain amplitude to the frequency resolution is determined, where the frequency resolution ratio is the reciprocal of the sampling time period of the first electrical signal. For example, if the sampling time period of the first electrical signal is 10 seconds, then the frequency resolution is 1 / 10.

[0100] There are several ways to determine the one-sided spectrum of the ratio of the mean square value of the frequency domain amplitude to the frequency resolution. In one example, the proportional value in the ratio is determined, and then multiplied by a preset value to obtain the first power spectral density of the first electrical signal. That is, the positive frequency part of the power spectral density is determined, and the corresponding amplitude is multiplied by the preset value. It should be noted that the preset value can be set according to the actual situation. In one example, the preset value is set to 2.

[0101] The method of switching the wind turbine to off-grid no-load mode to collect the second electrical signal and performing frequency domain analysis on the second electrical signal to obtain the second power spectral density is the same as the method of performing frequency domain analysis on the first electrical signal to obtain the first power spectral density, and will not be elaborated here.

[0102] There are multiple ways to determine whether the first power spectral density of the first electrical signal contains characteristic frequency components of wind turbine main bearing faults. In one example, refer to... Figure 4 Here is a flowchart of the steps of the fault detection method provided in this application embodiment, including:

[0103] Step 203-1: Determine the first amplitude of each peak in the first power spectral density.

[0104] Step 203-2: Determine the minimum and maximum amplitude values ​​among the first amplitude values.

[0105] Step 203-3: Calculate the product of the minimum amplitude and the preset multiple.

[0106] Step 203-4: When the maximum amplitude is greater than the product, determine the frequency corresponding to the maximum amplitude.

[0107] Step 203-5: Match the frequency with the characteristic frequencies of each component of the wind turbine.

[0108] Step 203-6: If the frequency matches the characteristic frequencies of each component of any wind turbine, determine that there is a wind turbine main bearing fault characteristic frequency component in the first power spectral density.

[0109] Step 203-7: Switch the wind turbine to off-grid no-load mode and collect the second electrical signal of the wind turbine.

[0110] like Figure 5 The diagram shown illustrates the first power spectral density of the first electrical signal. In one example, it is determined that... Figure 5 For each peak in the signal, the first amplitude is used to determine the maximum and minimum amplitudes. The minimum amplitude is then multiplied by a preset multiple. If the maximum amplitude is greater than the product of the minimum amplitude and the preset multiple, it is determined whether the frequency corresponding to the maximum amplitude belongs to the characteristic frequency of each component of the wind turbine. If so, the first power spectral density of the first electrical signal is determined to contain the characteristic frequency of the wind turbine main bearing fault. If not, the first power spectral density of the first electrical signal is determined to not contain the characteristic frequency of the wind turbine main bearing fault.

[0111] In another example, the first amplitude of each peak in the first power spectral density of the first electrical signal is determined, and each first peak is multiplied by a preset multiple to obtain multiple products. For each first amplitude, the first amplitude is compared with other products except the product of the first amplitude and the preset multiple. If the amplitude is greater than any product other than the product of the first amplitude and the preset multiple, the frequency corresponding to the first amplitude is determined. If the frequency corresponding to the first amplitude matches the characteristic frequency of each component of any wind turbine, then it is determined that the first power spectral density corresponding to the first electrical signal contains the characteristic frequency component of the wind turbine main bearing.

[0112] It should be noted that a wind turbine may include an outer ring component, an inner ring component, a rolling element component, a first cage component, and a second cage component, and different components correspond to different characteristic frequencies.

[0113] The characteristic frequencies of the outer ring components satisfy the following formula:

[0114]

[0115] The characteristic frequencies of the inner ring components satisfy the following formula:

[0116]

[0117] The characteristic frequencies of the rolling element components satisfy the following formula:

[0118]

[0119] The characteristic frequency of the first cage component satisfies the following formula:

[0120]

[0121] The characteristic frequency of the second cage component satisfies the following formula:

[0122]

[0123] Where Z is the number of rolling elements, d is the diameter of the rolling elements, D is the pitch diameter of the main bearing, α is the contact angle of the main bearing, and f is the contact angle of the main bearing. r The rotational frequency of the main bearing.

[0124] The frequency corresponding to the first amplitude that meets the above conditions is compared with the characteristic frequencies of the outer ring component, the inner ring component, the rolling element component, the first cage component, and the second cage component, respectively. If the frequency corresponding to the first amplitude that meets the above conditions matches the characteristic frequencies of any component of the wind turbine, it is determined that there is a characteristic frequency component of the wind turbine main bearing fault in the first power spectral density. At this time, the wind turbine is switched to off-grid no-load mode, and the second electrical signal of the wind turbine is collected. At the same time, a warning signal for the wind turbine main bearing fault is output, wherein the warning signal indicates that there may be a fault in the wind turbine main bearing.

[0125] Please refer to Figure 6 This application embodiment also provides an application for Figure 1 The fault detection device 110 of the electronic device 100 includes:

[0126] The first acquisition module 111 is used to acquire the first electrical signal of the wind turbine when the wind turbine is in the power generation operation mode.

[0127] The first analysis module 112 is used to perform frequency domain analysis on the first electrical signal to obtain the first power spectral density of the first electrical signal.

[0128] The second acquisition module 113 is used to switch the wind turbine to off-grid no-load mode and acquire the second electrical signal of the wind turbine when the main bearing fault characteristic frequency component of the wind turbine is present in the first power spectral density.

[0129] The second analysis module 114 is used to perform frequency domain analysis on the second electrical signal to obtain the second power spectral density of the second electrical signal.

[0130] The determination module 115 is used to determine that the main bearing of the wind turbine has failed when the main bearing failure characteristic frequency component of the wind turbine is present in the second power spectral density.

[0131] It should be noted that the fault detection device provided in this embodiment has the same basic principle and technical effect as the fault detection method embodiment described above. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content in the above method embodiment.

[0132] This application also provides an electronic device 100, which includes a processor 130 and a memory 120. The memory 120 stores computer-executable instructions, which, when executed by the processor 130, implement the fault detection method.

[0133] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor 130, implements the fault detection method.

[0134] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0135] Furthermore, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part. If the function is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0136] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0137] The above descriptions are merely various embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A fault detection method, characterized in that, The method includes: When the wind turbine is in power generation mode, the first electrical signal of the wind turbine is collected. Frequency domain analysis is performed on the first electrical signal to obtain the first power spectral density of the first electrical signal; When the wind turbine main bearing fault characteristic frequency component exists in the first power spectral density, the wind turbine is switched to off-grid no-load mode, and the second electrical signal of the wind turbine is collected. Frequency domain analysis of the second electrical signal yields the second power spectral density of the second electrical signal; When the main bearing fault characteristic frequency component of the wind turbine is present in the second power spectral density, it is determined that the main bearing of the wind turbine has failed. The step of switching the wind turbine to off-grid no-load mode and collecting the second electrical signal of the wind turbine when the first power spectral density contains a fault characteristic frequency component of the wind turbine main bearing includes: Determine the first amplitude of each peak in the first power spectral density; Determine the minimum and maximum amplitude values ​​among the first amplitude values; Calculate the product of the minimum amplitude and a preset multiple, where the preset multiple is 2; When the maximum amplitude value is greater than the product, the frequency corresponding to the maximum amplitude value is determined; The frequency is matched with the characteristic frequencies of each component of the wind turbine. If the frequency matches the characteristic frequency of any component of the wind turbine, it is determined that the first power spectral density contains a wind turbine main bearing fault characteristic frequency component. The wind turbine is switched to off-grid no-load mode, and the second electrical signal of the wind turbine is collected.

2. The method according to claim 1, characterized in that, The step of performing frequency domain analysis on the first electrical signal to obtain the first power spectral density of the first electrical signal includes: The first electrical signal is segmented to obtain multiple segmented electrical signals; The frequency domain amplitude of the first electrical signal is obtained by sequentially performing Fourier transform on the multiple segmented electrical signals. Calculate the mean square value of the frequency domain amplitude; Determine the ratio of the mean square value to the frequency resolution; The ratio is converted into a single-sided spectrum to obtain the first power spectral density of the first electrical signal.

3. The method according to claim 2, characterized in that, The step of converting the ratio into a single-sided spectrum to obtain the first power spectral density of the first electrical signal includes: Determine the proportional value in the ratio; Multiplying the proportional value by a preset value yields the first power spectral density of the first electrical signal.

4. The method according to claim 1, characterized in that, The wind turbine unit includes an outer ring component, an inner ring component, a rolling element component, a first cage component, and a second cage component; The characteristic frequency of the outer ring component satisfies the following formula: The characteristic frequency of the inner ring component satisfies the following formula: The characteristic frequency of the rolling element component satisfies the following formula: The characteristic frequency of the first cage component satisfies the following formula: The characteristic frequency of the second cage component satisfies the following formula: Where Z is the number of rolling elements, d is the diameter of the rolling elements, D is the pitch diameter of the main bearing, α is the contact angle of the main bearing, and f is the contact angle of the main bearing. r The rotational frequency of the main bearing.

5. The method according to claim 2, characterized in that, The step of segmenting the first electrical signal to obtain multiple segmented electrical signals includes: The first electrical signal is segmented through a Hamming window to obtain multiple segmented electrical signals.

6. The method according to claim 1, characterized in that, Following the step of identifying the characteristic frequency components of wind turbine main bearing faults in the first power spectral density, the method further includes: Output a warning signal for a fault in the main bearing of the wind turbine.

7. A fault detection device, characterized in that, The device includes: The first acquisition module is used to acquire the first electrical signal of the wind turbine when the wind turbine is in power generation operation mode; The first analysis module is used to perform frequency domain analysis on the first electrical signal to obtain the first power spectral density of the first electrical signal. The second acquisition module is used to switch the wind turbine to off-grid no-load mode and acquire the second electrical signal of the wind turbine when the main bearing fault characteristic frequency component of the wind turbine is present in the first power spectral density. The second analysis module is used to perform frequency domain analysis on the second electrical signal to obtain the second power spectral density of the second electrical signal; The determination module is used to determine that the main bearing of the wind turbine has failed when the main bearing fault characteristic frequency component of the wind turbine exists in the second power spectral density. Specifically, the determining module is used for: Determine the first amplitude of each peak in the first power spectral density; Determine the minimum and maximum amplitude values ​​among the first amplitude values; Calculate the product of the minimum amplitude and a preset multiple, where the preset multiple is 2; When the maximum amplitude value is greater than the product, the frequency corresponding to the maximum amplitude value is determined; The frequency is matched with the characteristic frequencies of each component of the wind turbine. If the frequency matches the characteristic frequency of any component of the wind turbine, it is determined that the first power spectral density contains a wind turbine main bearing fault characteristic frequency component. The wind turbine is switched to off-grid no-load mode, and the second electrical signal of the wind turbine is collected.

8. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method described in any one of claims 1-6.

Images