Fan fault detection method and device, electronic equipment, storage medium and program product
By acquiring the target sound signal of the wind turbine, performing signal separation and filtering, and combining cepstral and periodic analysis, the problem of accuracy in detecting blade bolt loss faults in wind turbines was solved, achieving efficient and accurate fault detection.
Patent Information
- Application Number
- CN202411251020.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2026-03-10
AI Technical Summary
Existing technologies have failed to effectively detect blade bolt failures in wind turbines, especially under the influence of changes in the external environment, where the complexity of sound signals makes it difficult to guarantee detection accuracy.
By acquiring the target sound signal of the wind turbine, performing signal separation and filtering, determining the cepstral spectrum, and combining it with signal periodicity analysis, the detection of bolt falling faults can be achieved.
It improves the accuracy and reliability of detecting loose bolts on wind turbine blades, simplifies the detection process, and reduces sensitivity to changes in the external environment.
Smart Images
Figure CN121630651A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of energy storage technology, specifically to a wind turbine fault detection method, device, electronic equipment, storage medium, and program product. Background Technology
[0002] A wind turbine is an electrical device that converts wind energy into mechanical work, which drives a rotor to rotate and ultimately outputs alternating current. During the operation of a wind turbine, if blade bolts fall off and cause a malfunction, it will lead to problems in the turbine's operation. Therefore, fault detection is necessary for wind turbines. Summary of the Invention
[0003] The purpose of this disclosure is to provide a wind turbine fault detection method, device, electronic equipment, storage medium, and program product that can effectively and accurately detect the failure of blade bolts falling off wind turbine generators.
[0004] To achieve the above objectives, in a first aspect, this disclosure provides a wind turbine fault detection method, comprising: acquiring a target sound signal corresponding to a wind turbine generator, the target sound signal being related to a blade fault of the wind turbine generator; determining the cepstral spectrum corresponding to the target sound signal; performing periodic analysis on the target sound signal to obtain a signal analysis result, the signal analysis result being used to characterize whether the target sound signal is a periodic signal that meets preset conditions; and determining a bolt loss fault detection result of the blade based on the cepstral spectrum corresponding to the target sound signal and the signal analysis result.
[0005] Optionally, acquiring the target sound signal corresponding to the wind turbine includes: acquiring the original sound signal collected by the sound acquisition device, wherein the location of the sound acquisition device is determined according to the windward side of the wind turbine and the radius of the blades; and performing signal processing on the original sound signal to obtain the target sound signal.
[0006] Optionally, the step of processing the original sound signal to obtain the target sound signal includes: performing signal separation processing on the original sound signal to obtain a separated signal, wherein the separated signal is a signal other than the blade sound signal; and performing signal filtering processing on the separated signal to obtain the target sound signal, wherein the target sound signal includes the hub sound signal of the wind turbine.
[0007] Optionally, determining the cepstrum corresponding to the target sound signal includes: performing a frequency domain transformation on the target sound signal to obtain a linear spectrum corresponding to the target sound signal; extracting the spectrum from the linear spectrum to obtain a logarithmic spectrum; and performing an inverse frequency domain transformation on the logarithmic spectrum to obtain the cepstrum.
[0008] Optionally, the preset condition is: the period of the target sound signal is a preset sound signal period, and the periodic analysis of the target sound signal to obtain the signal analysis result includes: obtaining the rotation angle of the blade; determining a first sound signal based on the rotation angle of the blade and the target sound signal; determining a second sound signal based on the rotation angle of the blade and the preset sound signal period; and determining the signal analysis result based on the first sound signal and the second sound signal.
[0009] Optionally, determining the signal analysis result based on the first sound signal and the second sound signal includes: if the first sound signal and the second sound signal match, determining that the signal analysis result indicates that the target sound signal is a periodic signal that meets a preset condition; if the first sound signal and the second sound signal do not match, determining that the signal analysis result indicates that the target sound signal is not a periodic signal that meets the preset condition.
[0010] Optionally, determining the bolt loss fault detection result of the blade based on the cepstral spectrum corresponding to the target sound signal and the signal analysis result includes: if the cepstral spectrum corresponding to the target sound signal determines that the target sound signal includes a target high-frequency signal, and the amplitude of the cepstral spectrum corresponding to the target high-frequency signal is greater than or equal to a preset amplitude, and the signal analysis result indicates that the target sound signal is a periodic signal that meets preset conditions, then the blade of the wind turbine is determined to have a bolt loss fault; if the cepstral spectrum corresponding to the target sound signal determines that the target sound signal does not include the target high-frequency signal, and / or the signal analysis result indicates that the target sound signal is not a periodic signal that meets preset conditions, then the blade of the wind turbine is determined not to have a bolt loss fault.
[0011] Secondly, this disclosure provides a wind turbine fault detection device, comprising: an acquisition module configured to acquire a target sound signal corresponding to a wind turbine generator, the target sound signal being related to a blade bolt falling off fault of the wind turbine generator; a determination module configured to determine the cepstral spectrum corresponding to the target sound signal; a signal analysis module configured to perform periodic analysis on the target sound signal to obtain a signal analysis result, the signal analysis result being used to characterize whether the target sound signal is a periodic signal that meets preset conditions; and a detection module configured to determine the detection result of the blade bolt falling off fault based on the cepstral spectrum corresponding to the target sound signal and the signal analysis result.
[0012] Thirdly, this disclosure provides an electronic device, comprising: a memory storing a computer program thereon; and a processor for executing the computer program in the memory to implement the wind turbine fault detection method described in the first aspect.
[0013] Fourthly, this disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the wind turbine fault detection method described in the first aspect.
[0014] Fifthly, this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the wind turbine fault detection method described in the first aspect.
[0015] The above technical solution acquires target sound signals related to wind turbine blade faults, determines the cepstrum based on these signals, and performs signal analysis to determine whether the target sound signal is a periodic signal that meets preset conditions. Then, combining the cepstrum and signal analysis results, the bolt loss fault detection result is determined. This fault detection scheme combines cepstrum analysis and signal analysis to integrate information from different dimensions, resulting in higher accuracy of the final bolt loss fault detection result and achieving effective and accurate detection of wind turbine blade bolt loss faults.
[0016] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description
[0017] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart illustrating a wind turbine fault detection method according to an exemplary embodiment.
[0018] Figure 2 This is a schematic diagram of a wind turbine generator according to an exemplary embodiment.
[0019] Figure 3 This is a block diagram illustrating a wind turbine fault detection device according to an exemplary embodiment.
[0020] Figure 4 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation
[0021] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.
[0022] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.
[0023] A wind turbine is an electrical device that converts wind energy into mechanical work, which drives a rotor to rotate and ultimately outputs alternating current. During the operation of a wind turbine, blade failure can cause problems, thus requiring fault detection.
[0024] For example, during the operation of a wind turbine, bolts on the blades may fall off. After falling off, these bolts may land inside the hub and rotate with it. This can cause not only blade malfunctions but also malfunctions inside the hub, thus affecting the operation of the wind turbine.
[0025] In related technologies, to detect faults in wind turbines, sound signals from the turbines are collected, and then a neural network model is used to detect these signals, yielding a bolt-falling fault detection result. However, this method fails to consider the susceptibility of sound signals to external environmental influences, such as seasonal changes and wind direction variations. In other words, it doesn't account for the complexity of sound signals, thus potentially compromising the accuracy of the final bolt-falling fault detection result.
[0026] Based on this, the present disclosure provides a fault detection scheme that combines cepstral spectrum analysis and signal analysis to achieve fault detection. This integrates information from different dimensions, which can reflect the complexity of the sound signal. As a result, the accuracy of the final bolt falling fault detection result is higher, achieving effective and accurate wind turbine blade fault detection.
[0027] Figure 1 This is a flowchart illustrating a wind turbine fault detection method according to an exemplary embodiment, the wind turbine fault detection method comprising the following steps: Step S11: Obtain the target sound signal corresponding to the wind turbine. The target sound signal is related to the blade fault of the wind turbine.
[0028] Step S12: Determine the cepstral frequency corresponding to the target sound signal.
[0029] Step S13: Perform periodic analysis on the target sound signal to obtain the signal analysis result. The signal analysis result is used to characterize whether the target sound signal is a periodic signal that meets the preset conditions.
[0030] Step S14: Determine the detection result of the bolt falling off the blade based on the cepstral spectrum corresponding to the target sound signal and the signal analysis results.
[0031] In step S11, the target sound signal can be a pre-processed sound signal related to a blade fault in a wind turbine. For example, it could be the sound signal generated after a bolt on a blade comes loose.
[0032] In some embodiments, step S11 may include: acquiring the original sound signal acquired by the sound acquisition device, wherein the location of the sound acquisition device is determined according to the windward side of the wind turbine and the radius of the blades; and performing signal processing on the original sound signal to obtain the target sound signal.
[0033] In this implementation, the original sound signal is acquired by a sound acquisition device, and signal processing is performed based on the original sound signal to obtain the target sound signal.
[0034] In some embodiments, the sound acquisition device may be located on the windward side of the wind turbine, and the distance from the center of the wind turbine is equal to the radius of the blade.
[0035] In some embodiments, a wind turbine may be equipped with multiple sound acquisition devices, which are respectively set in different locations to achieve multi-point sound signal acquisition.
[0036] In some embodiments, the sound signals processed in steps S11 to S14 may be sound signals obtained based on multi-point sound signals. For example, the multi-point sound signals are integrated to obtain the final sound signal used for fault detection.
[0037] In some embodiments, the different positions of multiple sound acquisition devices can be configured in conjunction with different windward surfaces. That is, sound acquisition devices can be configured under different windward surface conditions, so that fault detection can be achieved under different windward surface conditions.
[0038] In some embodiments, the sound acquisition device may be a microphone or a microphone array, etc., which are not limited herein.
[0039] Figure 2 This is a schematic diagram of a wind turbine generator according to an exemplary embodiment, such as... Figure 2 As shown, the radius of the wind turbine blade is R. Draw a perpendicular line from the tip position A of any blade to the ground, and let B be the point on the ground. The sound acquisition device can be set at a position between points A and B on the perpendicular line.
[0040] For example, a sound acquisition device fixing device is set at point B. The height of the fixing device can be less than the length of the vertical line AB. By fixing the sound acquisition device on the fixing device, the sound signal matching the windward side can be acquired.
[0041] Understandable. Figure 2 The windward side shown is clockwise. Under the clockwise windward side, sound acquisition devices can also be configured based on points B' and A'. Point B' and point B are symmetrical points based on point O, and point A' and point A are symmetrical points based on point O. Point O can be the center point of the wind turbine.
[0042] Alternatively, in other windward situations, set up the corresponding sound acquisition device in the manner described above.
[0043] In some embodiments, when multiple sound acquisition devices are provided, the multiple sound acquisition devices can be spaced apart by a certain angle.
[0044] In some embodiments, the original sound signal is the original sound signal acquired within the sound signal acquisition period, which may include sound signals at multiple time points.
[0045] In some embodiments, the sound acquisition device can acquire sound signals based on the operating status of the wind turbine. Therefore, the wind turbine can also be equipped with an encoder, which can acquire information such as the wind turbine's rotation angle and number of revolutions.
[0046] For example, sound signals can be collected when the rotation angle of the wind turbine is 0, that is, when the wind turbine is not rotating.
[0047] In other embodiments, the sound acquisition device may also acquire sound signals at regular intervals, such as every 10 minutes, 20 minutes, etc.
[0048] In some embodiments, the sound acquisition device may continuously acquire sound signals, but fault detection is periodic. For example, every hour, the raw sound signals acquired by the sound acquisition device within that hour are acquired, and fault detection is performed.
[0049] Through the above implementation method, a multi-point acquisition approach is adopted, with acquisition points distributed in a fan shape in front of the wind turbine, effectively collecting sound signals from wind turbine blades on different windward sides. This improves signal processing performance, as the acquisition effect is not affected by different wind directions, resulting in more comprehensive sound acquisition and establishing a solid data foundation for subsequent sound signal processing.
[0050] In some embodiments, processing the original sound signal to obtain a target sound signal may include: performing signal separation processing on the original sound signal to obtain a separated signal, wherein the separated signal is a signal other than the blade sound signal; and performing signal filtering processing on the separated signal to obtain the target sound signal, wherein the target sound signal includes the hub sound signal of the wind turbine.
[0051] In this implementation, signal separation can be achieved through blind source separation. It can be understood that since the sound signal generated by a fault can generally be defined as noise, and noise and the blade sound signal are not from the same source, satisfying the independent condition for blind source separation, the blade sound signal and noise signal can be separated through blind source separation. That is, the separated signal can be understood as a type of noise signal.
[0052] In some embodiments, blind source separation can be achieved using the Fast ICA (Independent Component Analysis) method, which can separate the leaf acoustic observation signal to obtain signals other than the leaf acoustic signal. For specific implementation details of this method, please refer to mature technologies in the field; they will not be described in detail here.
[0053] Furthermore, based on the separated signals, signal filtering is performed to remove invalid signals, thereby obtaining the hub sound signal of the wind turbine. As mentioned in the previous embodiment, if a bolt falls off, it will fall into the hub and cause an impact, so the hub sound signal may be altered. Therefore, the hub sound signal can be considered as a signal related to blade failure.
[0054] In some embodiments, signal filtering can be achieved using a Mel filter. This filter works by convolving the input signal with a specific frequency response function, thereby modifying and filtering the signal spectrum. Typically, it can also emphasize the high-frequency components of the audio signal before filtering.
[0055] In some embodiments, the sound produced by a bolt falling out and landing inside the wheel hub is a periodic impact sound, which has two characteristics: a high sound frequency and periodicity.
[0056] Therefore, the cepstral spectrum can be determined to determine whether the characteristic of a high sound frequency is met; and the periodicity analysis results can be determined to determine whether the characteristic of periodicity is met. Furthermore, it can be determined whether the target sound signal is a fault-caused sound signal, thus achieving fault detection.
[0057] In step S12, the cepstrum corresponding to the target sound signal is determined. The cepstrum can be determined through spectrum analysis.
[0058] As an optional implementation, step S12 includes: performing frequency domain transformation on the target sound signal to obtain the linear spectrum corresponding to the target sound signal; extracting the spectrum from the linear spectrum to obtain the logarithmic spectrum; and performing inverse frequency domain transformation on the logarithmic spectrum to obtain the cepstrum.
[0059] In some embodiments, the signal is converted from the time domain to the frequency domain by short-time Fourier transform to obtain the linear spectrum of the target sound signal.
[0060] In some embodiments, the linear spectrum is extracted using a Mel filter, and the logarithm of the Mel spectrum is taken to obtain the logarithmic spectrum.
[0061] In some embodiments, an inverse frequency domain transform is performed based on the logarithmic spectrum, and the real part is extracted and its absolute value is taken to obtain the cepstrum. The inverse frequency domain transform is, for example, the inverse Fourier transform.
[0062] The cepstral spectrum reflects the amplitude of periodic sound signals at different frequencies. Based on this amplitude, it can be determined whether the target sound signal matches the characteristics of a fault sound signal.
[0063] In some embodiments, if the target sound signal is a sound signal over a relatively long period of time, the sound signal can be segmented into frames before determining the cepstrum, and then the cepstrum can be determined frame by frame to reduce the difficulty of spectrum determination.
[0064] In step S13, the target sound signal is periodically analyzed to obtain the signal analysis results.
[0065] In some embodiments, since steps S12 and S13 are two independent signal processing steps, the processing order of steps S12 and S13 is not limited.
[0066] In some embodiments, the purpose of periodic signal analysis is to determine whether the target sound signal is a periodic signal that meets preset conditions. Therefore, the signal analysis results can characterize whether the target sound signal is a periodic signal that meets preset conditions.
[0067] In some embodiments, the preset condition is that the period of the target sound signal is a preset sound signal period. That is, the sound signal characterizing the fault is not only a periodic signal, but its signal period is also a preset sound signal period.
[0068] The preset sound signal period can be determined based on the number of blades. For example, if the number of blades is 3, then the preset sound signal period is an integer multiple of π / 3.
[0069] Furthermore, step S13 may include: acquiring the rotation angle of the blade; determining a first sound signal based on the rotation angle of the blade and the target sound signal; determining a second sound signal based on the rotation angle of the blade and a preset sound signal period; and determining the signal analysis result based on the first sound signal and the second sound signal.
[0070] In some embodiments, an encoder mounted on the wind turbine can detect the rotation angle, so the blade's rotation angle can be obtained from the encoder. This blade rotation angle can be understood as the angle to which the blade has currently rotated.
[0071] Based on the blade rotation angle, using the target sound signal, a first sound signal at that rotation angle can be determined; for example, the first sound signal is the target sound signal. Based on the blade rotation angle and a preset sound signal period, a second sound signal after the preset sound signal period can be determined. Therefore, the second sound signal can be understood as the sound signal collected after the preset sound signal period, and the acquisition method of this sound signal can be the same as the acquisition method of the target sound signal. Alternatively, the sound signal after the preset sound signal period can be predicted based on the characteristics of the target sound signal, and this predicted sound signal can be determined as the second sound signal.
[0072] Further, based on the first sound signal and the second sound signal, the signal analysis result is determined, including: if the first sound signal and the second sound signal match, the signal analysis result indicates that the target sound signal is a periodic signal that meets the preset conditions; if the first sound signal and the second sound signal do not match, the signal analysis result indicates that the target sound signal is not a periodic signal that meets the preset conditions.
[0073] Whether the first and second sound signals match can be determined based on the average amplitude difference function, which can determine the periodicity of the sound signal array.
[0074] Example, constructor , The sound signal collected when the blade rotates to an angle of m, i.e., x angle (m).
[0075] The average amplitude difference function is used to determine the periodicity of the audio signal array:
[0076] in, , The function represents the average amplitude difference, and N represents the length of the original audio signal. . To preset the sound signal period, due to the symmetry of the fan blades, therefore... represent Integer multiples of. It can be considered as the first sound signal. It can be considered a second sound signal.
[0077] when When the value is close to zero, the The value is the period of the sound signal. Therefore, when this... When the value is close to zero, it means that the first sound signal and the second sound signal match; otherwise, the first sound signal and the second sound signal do not match.
[0078] In some embodiments, based on a preset sound signal period, other periodic signal determination methods can also be used to obtain signal analysis results.
[0079] Furthermore, in step S14, the detection result of the bolt falling off the blade is determined based on the cepstral spectrum corresponding to the target sound signal and the signal analysis result.
[0080] As an optional implementation, step S14 includes: if the target sound signal is determined to include a target high-frequency signal based on the cepstral spectrum corresponding to the target sound signal, and the amplitude of the cepstral spectrum corresponding to the target high-frequency signal is greater than or equal to a preset amplitude, and the signal analysis result indicates that the target sound signal is a periodic signal that meets the preset conditions, then it is determined that the wind turbine blade has a bolt falling off fault; if the target sound signal is determined to not include a target high-frequency signal based on the cepstral spectrum corresponding to the target sound signal, and / or the signal analysis result indicates that the target sound signal is not a periodic signal that meets the preset conditions, then it is determined that the wind turbine blade does not have a bolt falling off fault.
[0081] In some embodiments, the horizontal axis of the cepstrum is the reciprocal of the frequency, and the vertical axis is the amplitude. The reciprocal of the frequency can be used to determine whether the target sound signal includes a target high-frequency signal. This target high-frequency signal can be a newly emerging high-frequency signal with a relatively high frequency.
[0082] Therefore, if the target sound signal is a high-frequency signal with a high amplitude and is a periodic signal that meets preset conditions, it can be determined that the wind turbine blades have a bolt loss fault. In other cases, it can be determined that the wind turbine blades do not have a bolt loss fault.
[0083] The wind turbine fault detection method according to the present disclosure does not require the prior collection of a large amount of data for pre-training, compared with the current machine learning methods, thus improving the generalizability of the method.
[0084] Therefore, the technical solution provided by the embodiments of this disclosure can not only achieve effective and accurate blade fault detection of wind turbines, but also achieve simpler and more applicable blade fault detection.
[0085] Furthermore, based on the bolt loss fault detection results, relevant users can be alerted to take appropriate action. For example, if the bolt loss fault detection results indicate that a bolt has fallen off the blade, a notification message can be sent to the maintenance user, enabling them to repair the bolt loss fault on the blade according to the notification message.
[0086] In some embodiments, in addition to detecting blade failures due to loose bolts, other types of failures can also be detected. For example, failure detection can be achieved based on the sound signal characteristics corresponding to other failure types; correspondingly, the signal analysis methods and the final failure determination methods may differ.
[0087] Figure 3 This is a block diagram illustrating a wind turbine fault detection device 300 according to an exemplary embodiment, such as... Figure 3 As shown, the wind turbine fault detection device 300 includes: The acquisition module 301 is configured to acquire a target sound signal corresponding to the wind turbine, the target sound signal being related to the blade bolt falling off fault of the wind turbine.
[0088] The determination module 302 is configured to determine the cepstral spectrum corresponding to the target sound signal.
[0089] The signal analysis module 303 is configured to perform periodic analysis on the target sound signal to obtain a signal analysis result, which is used to characterize whether the target sound signal is a periodic signal that meets preset conditions.
[0090] The detection module 304 is configured to determine the bolt loss fault detection result of the blade based on the cepstral spectrum corresponding to the target sound signal and the signal analysis result.
[0091] Optionally, the acquisition module 301 is further configured to: acquire the original sound signal collected by the sound acquisition device, wherein the location of the sound acquisition device is determined according to the windward side of the wind turbine and the radius of the blade; and perform signal processing on the original sound signal to obtain the target sound signal.
[0092] Optionally, the acquisition module 301 is further configured to: perform signal separation processing on the original sound signal to obtain a separated signal, wherein the separated signal is a signal other than the blade sound signal; and perform signal filtering processing on the separated signal to obtain the target sound signal, wherein the target sound signal includes the hub sound signal of the wind turbine.
[0093] Optionally, the determining module 302 is further configured to: perform frequency domain transformation on the target sound signal to obtain the linear spectrum corresponding to the target sound signal; perform spectrum extraction on the linear spectrum to obtain the logarithmic spectrum; and perform inverse frequency domain transformation on the logarithmic spectrum to obtain the cepstrum.
[0094] Optionally, the signal analysis module 303 is further configured to acquire the rotation angle of the blade; determine a first sound signal based on the rotation angle of the blade and the target sound signal; determine a second sound signal based on the rotation angle of the blade and the preset sound signal period; and determine the signal analysis result based on the first sound signal and the second sound signal.
[0095] Optionally, the signal analysis module 303 is further configured to, if the first sound signal and the second sound signal match, determine that the signal analysis result indicates that the target sound signal is a periodic signal that meets a preset condition; if the first sound signal and the second sound signal do not match, determine that the signal analysis result indicates that the target sound signal is not a periodic signal that meets a preset condition.
[0096] Optionally, the detection module 304 is further configured to: if the cepstral spectrum corresponding to the target sound signal determines that the target sound signal includes a target high-frequency signal, and the amplitude of the cepstral spectrum corresponding to the target high-frequency signal is greater than or equal to a preset amplitude, and the signal analysis result indicates that the target sound signal is a periodic signal that meets the preset conditions, then determine that the blade of the wind turbine has a bolt falling off fault; if the cepstral spectrum corresponding to the target sound signal determines that the target sound signal does not include the target high-frequency signal, and / or the signal analysis result indicates that the target sound signal is not a periodic signal that meets the preset conditions, then determine that the blade of the wind turbine does not have a bolt falling off fault.
[0097] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.
[0098] Figure 4 This is a block diagram illustrating an electronic device 400 according to an exemplary embodiment. Figure 4 As shown, the electronic device 400 may include a processor 401 and a memory 402. The electronic device 400 may also include one or more of a multimedia component 403, an input / output (I / O) interface 404, and a communication component 405.
[0099] The processor 401 controls the overall operation of the electronic device 400 to complete all or part of the steps in the aforementioned wind turbine fault detection method. The memory 402 stores various types of data to support the operation of the electronic device 400. This data may include, for example, instructions for any application or method operating on the electronic device 400, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 402 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 403 may include a screen and audio components. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 402 or transmitted via communication component 405. The audio component also includes at least one speaker for outputting audio signals. I / O interface 404 provides an interface between processor 401 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 405 is used for wired or wireless communication between the electronic device 400 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G technologies, or combinations thereof, is not limited here. Therefore, the corresponding communication component 405 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.
[0100] In an exemplary embodiment, the electronic device 400 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the wind turbine fault detection method described above.
[0101] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the wind turbine fault detection method described above. For example, the computer-readable storage medium may be the memory 402 including program instructions, which may be executed by the processor 401 of the electronic device 400 to complete the wind turbine fault detection method described above.
[0102] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.
[0103] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.
[0104] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.
Claims
1. A method of detecting a fault in a fan, the method comprising: The method comprises the following steps: obtaining a target sound signal corresponding to a wind turbine, the target sound signal being related to a bolt falling fault of a blade of the wind turbine; determining a cepstrum corresponding to the target sound signal; performing periodicity analysis on the target sound signal to obtain a signal analysis result, the signal analysis result being used to represent whether the target sound signal is a periodic signal meeting a preset condition; determining a bolt falling fault detection result of the blade according to the cepstrum corresponding to the target sound signal and the signal analysis result.
2. The fan fault detection method of claim 1, wherein The method comprises the following steps: obtaining an original sound signal collected by a sound collecting device, wherein a setting position of the sound collecting device is determined according to a windward surface of the wind turbine and a radius of the blade; performing signal processing on the original sound signal to obtain the target sound signal.
3. The fan fault detection method of claim 2, wherein The method comprises the following steps: performing signal separation processing on the original sound signal to obtain a separated signal, the separated signal being a signal other than a blade sound signal; performing signal filtering processing on the separated signal to obtain the target sound signal, the target sound signal comprising a hub sound signal of the wind turbine.
4. The fan fault detection method of claim 1, wherein The method comprises the following steps: performing frequency domain transformation on the target sound signal to obtain a linear spectrum corresponding to the target sound signal; performing spectrum extraction on the linear spectrum to obtain a logarithmic spectrum; performing inverse frequency domain transformation on the logarithmic spectrum to obtain the cepstrum.
5. The fan fault detection method of claim 1, wherein The preset condition is that a period of the target sound signal is a preset sound signal period, and the method comprises the following steps: obtaining a rotation angle of the blade; determining a first sound signal according to the rotation angle of the blade and the target sound signal; determining a second sound signal according to the rotation angle of the blade and the preset sound signal period; determining the signal analysis result according to the first sound signal and the second sound signal.
6. The fan fault detection method of claim 5, wherein The method comprises the following steps: if the first sound signal and the second sound signal match, determining that the signal analysis result represents that the target sound signal is a periodic signal meeting a preset condition; if the first sound signal and the second sound signal do not match, determining that the signal analysis result represents that the target sound signal is not a periodic signal meeting a preset condition.
7. The fan fault detection method according to any one of claims 1 to 6, characterized in that, The method comprises the following steps: if it is determined according to the cepstrum corresponding to the target sound signal that the target sound signal comprises a target high frequency signal and a cepstrum amplitude corresponding to the target high frequency signal is greater than or equal to a preset amplitude, and the signal analysis result represents that the target sound signal is a periodic signal meeting a preset condition, determining that the blade of the wind turbine has a bolt falling fault. If it is determined according to the cepstrum corresponding to the target sound signal that the target sound signal does not include the target high-frequency signal, and / or the signal analysis result indicates that the target sound signal is not a periodic signal satisfying a preset condition, it is determined that the blade of the wind turbine does not have a bolt falling fault.
8. A fan fault detection apparatus, characterized by, Comprise: An acquisition module configured to acquire a target sound signal corresponding to a wind turbine, the target sound signal being related to a bolt falling fault of a blade of the wind turbine; A determination module configured to determine a cepstrum corresponding to the target sound signal; A signal analysis module configured to perform periodic analysis on the target sound signal to obtain a signal analysis result, the signal analysis result being used to indicate whether the target sound signal is a periodic signal satisfying a preset condition; A detection module configured to determine a bolt falling fault detection result of the blade according to the cepstrum corresponding to the target sound signal and the signal analysis result.
9. The fan fault detection apparatus of claim 8, wherein The acquisition module is further configured to: acquire an original sound signal collected by a sound collection device, wherein a setting position of the sound collection device is determined according to a windward surface of the wind turbine and a radius of the blade; Perform signal processing on the original sound signal to obtain the target sound signal.
10. The blower fault detection apparatus of claim 8, wherein The determination module is further configured to: Perform frequency domain transformation on the target sound signal to obtain a linear spectrum corresponding to the target sound signal; Perform spectrum extraction on the linear spectrum to obtain a logarithmic spectrum; Perform inverse frequency domain transformation on the logarithmic spectrum to obtain the cepstrum.
11. The blower fault detection apparatus of claim 8, wherein The preset condition is that a period of the target sound signal is a preset sound signal period, and the signal analysis module is further configured to: Acquire a rotation angle of the blade; Determine a first sound signal according to the rotation angle of the blade and the target sound signal; Determine a second sound signal according to the rotation angle of the blade and the preset sound signal period; Determine the signal analysis result according to the first sound signal and the second sound signal.
12. The blower fault detection apparatus of claim 8, wherein, The detection module is further configured to: If it is determined according to the cepstrum corresponding to the target sound signal that the target sound signal includes a target high-frequency signal, and a cepstrum corresponding to the target high-frequency signal is greater than or equal to a preset amplitude, and the signal analysis result indicates that the target sound signal is a periodic signal satisfying a preset condition, it is determined that the blade of the wind turbine has a bolt falling fault; If it is determined according to the cepstrum corresponding to the target sound signal that the target sound signal does not include the target high-frequency signal, and / or the signal analysis result indicates that the target sound signal is not a periodic signal satisfying a preset condition, it is determined that the blade of the wind turbine does not have a bolt falling fault.
13. An electronic device, comprising: Comprise: A memory having a computer program stored thereon; A processor configured to execute the computer program in the memory to implement the wind turbine fault detection method in any one of claims 1-7.
14. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the wind turbine fault detection method in any one of claims 1-7. The computer program is executed by the processor to implement the wind turbine fault detection method in any one of claims 1-7.
15. A computer program product, characterised in that, The computer program comprises a computer program which, when executed by a processor, implements the fan fault detection method according to any one of claims 1-7.