Methods, devices, equipment and storage media for early warning of abnormal vibration of wind turbine units

Abstract

This application discloses a method, device, equipment, and storage medium for early warning of abnormal vibration in wind turbine generators, relating to the field of wind turbine technology. The method includes: acquiring raw sensor signals during the operation of the wind turbine generator through a sensor array and performing spectral analysis to determine abnormal spectral characteristics; determining abnormal vibration regions based on the abnormal spectral characteristics and the sensor array; and comparing the abnormal spectral characteristics with a spectral database based on the abnormal vibration regions to obtain abnormal vibration values ​​of the wind turbine generator, thereby providing an early warning of abnormalities in the wind turbine generator. Because this application monitors the raw sensor signals during the operation of the wind turbine generator through a sensor array and performs spectral analysis to determine abnormal spectral characteristics, the abnormal vibration regions and abnormal vibration values ​​of the wind turbine generator during operation can be determined using these abnormal spectral characteristics. This allows for timely maintenance of the wind turbine generator that may fail, achieving timely early warning of abnormal vibration in the wind turbine generator and preventing vibration failures.

Description

Technical Field

[0001] This application relates to the field of wind turbine technology, and in particular to an abnormal vibration early warning method, device, equipment and storage medium for wind turbine units. Background Technology

[0002] Wind energy is a renewable energy source, and generating electricity using wind power is a common method of power generation. Wind power generation is achieved by converting the mechanical energy of wind into electrical energy through wind turbine units. A wind turbine unit mainly consists of three parts: blades, nacelle, and tower. The blades are connected to the generator in the nacelle through a main shaft, so that when the blades rotate under the action of wind, they can drive the generator to generate electricity, thereby realizing the conversion of wind energy into electrical energy.

[0003] During the process of converting wind mechanical energy into electrical energy, many components of a wind turbine will vibrate. Under normal circumstances, this vibration does not affect the operation of the wind turbine. However, because the main bearing, gearbox, coupling, generator, and blades of a wind turbine form a large mechanical transmission chain system, any problem in any of these components (such as blade corrosion, leading and trailing edge blade cracking, imbalance, or loosening of shaft components) will lead to increased vibration. When the vibration reaches a certain level, it will cause a vibration failure, thereby damaging the entire wind turbine.

[0004] Therefore, how to detect the vibration status of wind turbines in order to make a quick and accurate diagnosis during the early warning period of a fault and prevent vibration failures in wind turbines is an urgent problem to be solved. Summary of the Invention

[0005] The main purpose of this application is to provide an abnormal vibration early warning method, device, equipment and storage medium for wind turbines, which aims to solve the technical problem that when any device in a wind turbine malfunctions, it can easily lead to increased vibration and vibration failure, thereby damaging the entire wind turbine.

[0006] To achieve the above objectives, this application proposes an abnormal vibration early warning method for wind turbine generators, the method comprising:

[0007] The raw sensing signals during the operation of the wind turbine are collected by a sensor array, which is installed on various components of the wind turbine.

[0008] Perform spectral analysis on the original sensing signal to determine abnormal spectral characteristics;

[0009] Based on the abnormal spectral characteristics and the sensor array, the abnormal vibration region of the wind turbine is determined;

[0010] The abnormal spectral characteristics of the wind turbine are compared with a preset spectrum database based on the abnormal vibration region to obtain the abnormal vibration value of the wind turbine. The spectrum database stores the conventional spectrum data of each component.

[0011] Anomaly warning is issued for the wind turbine based on the abnormal vibration value of the wind turbine.

[0012] In one embodiment, the step of performing spectral analysis on the original sensing signal to determine abnormal spectral characteristics includes:

[0013] The original vibration signal and the original sound signal are extracted from the original sensing signal, and the sensor array includes a sound sensor and a vibration sensor;

[0014] The original vibration signal is subjected to spectral analysis by fast Fourier transform to obtain the abnormal vibration peak value and the corresponding frequency variation characteristics of the original vibration signal.

[0015] Harmonic analysis is performed on the original sound signal to obtain the abnormal harmonics of the original sound signal;

[0016] The abnormal vibration peak value, the frequency variation characteristics, and the abnormal harmonics are used as the abnormal spectral characteristics of the original sensing signal.

[0017] In one embodiment, the step of performing spectral analysis on the original vibration signal using Fast Fourier Transform to obtain the abnormal vibration peak value and corresponding frequency variation characteristics of the original vibration signal includes:

[0018] The original vibration signal is filtered to obtain the filtered vibration signal;

[0019] The filtered vibration signal is converted from the time domain to the frequency domain by a fast Fourier transform to obtain a frequency domain vibration signal.

[0020] The frequency domain vibration signal was subjected to spectral analysis to obtain the abnormal vibration peak value;

[0021] Time-frequency analysis is performed based on the abnormal vibration peak value to determine the frequency variation characteristics corresponding to the abnormal vibration peak value.

[0022] In one embodiment, the step of performing harmonic analysis on the original sound signal to obtain the abnormal harmonics of the original sound signal includes:

[0023] The original sound signal is subjected to noise reduction processing to obtain the target sound signal;

[0024] The intensity of the target sound signal is measured to obtain the corresponding sound intensity value.

[0025] Harmonic analysis is performed on the target sound signal to determine its harmonic characteristics;

[0026] Based on the sound intensity value and the harmonic characteristics, the original sound signal is subjected to spectral analysis to determine the abnormal harmonics of the original sound signal.

[0027] In one embodiment, the step of comparing the abnormal spectral features with a preset spectral database based on the abnormal vibration region to obtain the abnormal vibration value of the wind turbine includes:

[0028] Extract the conventional spectrum data corresponding to the abnormal vibration region from the preset spectrum database;

[0029] The regular spectrum data is compared with the abnormal spectrum features to obtain the corresponding frequency deviation data and amplitude change data;

[0030] Based on the frequency deviation data, the amplitude change data, and the preset weight value, the abnormal vibration value of the wind turbine is determined.

[0031] In one embodiment, after the step of providing an anomaly warning for the wind turbine based on the abnormal vibration value of the wind turbine, the method further includes:

[0032] Determine whether the abnormal vibration value of the wind turbine unit reaches a preset threshold;

[0033] When the abnormal vibration value of the wind turbine reaches the preset threshold, it is determined that there are damaged components in the wind turbine, and the fault type and component health of the damaged components are determined by the abnormal vibration value of the wind turbine.

[0034] A maintenance strategy is generated based on the fault type, the component health status, and the damaged component data.

[0035] The maintenance strategy is sent to maintenance personnel so that they can perform maintenance on the wind turbine according to the maintenance strategy.

[0036] Furthermore, to achieve the above objectives, this application also proposes an abnormal vibration early warning device for wind turbine generators, the device comprising:

[0037] The signal acquisition module is used to acquire raw sensing signals during the operation of the wind turbine through a sensor array, which is installed on various components of the wind turbine.

[0038] The spectrum analysis module is used to perform spectrum analysis on the original sensing signal to determine abnormal spectrum characteristics;

[0039] The region determination module is used to determine the abnormal vibration region of the wind turbine based on the abnormal spectrum characteristics and the sensor array.

[0040] The database comparison module is used to compare the abnormal spectral characteristics with a preset spectrum database based on the abnormal vibration area to obtain the abnormal vibration value of the wind turbine. The spectrum database stores the conventional spectrum data of each component.

[0041] An anomaly warning module is used to provide anomaly warnings for the wind turbine based on the abnormal vibration values ​​of the wind turbine.

[0042] In addition, to achieve the above objectives, this application also proposes an abnormal vibration early warning device for wind turbines, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the abnormal vibration early warning method for wind turbines as described above.

[0043] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the abnormal vibration early warning method for wind turbines as described above.

[0044] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the abnormal vibration early warning method for wind turbines as described above.

[0045] One or more technical solutions proposed in this application have at least the following technical effects: The abnormal vibration early warning method for wind turbine generators in this application includes: collecting raw sensing signals during the operation of the wind turbine generator through a sensor array, wherein the sensor array is installed on various components of the wind turbine generator; performing spectral analysis on the raw sensing signals to determine abnormal spectral characteristics; determining the abnormal vibration region of the wind turbine generator based on the abnormal spectral characteristics and the sensor array; comparing the abnormal spectral characteristics with a preset spectral database based on the abnormal vibration region to obtain the abnormal vibration value of the wind turbine generator, wherein the spectral database stores the conventional spectral data of each component; and providing an abnormal early warning for the wind turbine generator based on the abnormal vibration value.

[0046] This application monitors the raw sensor signals during the operation of the wind turbine using a sensor array and performs spectral analysis on these signals to determine abnormal spectral characteristics. These abnormal spectral characteristics allow for the identification of abnormal vibration regions and values ​​during wind turbine operation. This enables timely maintenance and repair of potentially faulty wind turbine units based on abnormal vibration values, providing early warning of abnormal vibrations and preventing vibration failures, thus ensuring reliable wind turbine operation. Attached Figure Description

[0047] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart illustrating an embodiment of the abnormal vibration early warning method for wind turbine generators in this application.

[0050] Figure 2 This is a flowchart illustrating Embodiment 2 of the abnormal vibration early warning method for wind turbine generators in this application.

[0051] Figure 3 This is a schematic diagram of the module structure of the abnormal vibration early warning device for wind turbine generators according to an embodiment of this application;

[0052] Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the abnormal vibration early warning method for wind turbines in this application embodiment.

[0053] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0054] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0055] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0056] It should be noted that the executing entity in this embodiment can be a computing service device with data acquisition, spectrum analysis, and anomaly early warning functions, such as a personal computer, a vibration detector, etc., or an electronic device capable of realizing the above functions, or an abnormal vibration early warning device for a wind turbine (hereinafter referred to as an early warning device) executing the abnormal vibration early warning method for wind turbines of this application, etc. This embodiment does not limit this. The following uses an early warning device as an example to describe this embodiment and the following embodiments.

[0057] Based on this, Embodiment 1 of this application is proposed. This embodiment of the application provides a method for early warning of abnormal vibration in wind turbine generators, referring to... Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the abnormal vibration early warning method for wind turbine generators in this application.

[0058] In this embodiment, the abnormal vibration early warning method for wind turbine generators includes steps S10 to S50:

[0059] Step S10: Collect raw sensing signals during the operation of the wind turbine through a sensor array, wherein the sensor array is installed on various components of the wind turbine.

[0060] Understandably, a wind turbine is a device that converts wind energy into electrical energy, mainly composed of blades, hub, nacelle, tower, and other parts. When the wind blows and the blades rotate, a series of mechanical and electrical systems drive the generator to operate, thereby generating electricity.

[0061] A sensor array can refer to an array formed by installing multiple sensors (including vibration sensors, sound sensors, etc.) in a certain arrangement on various components of a wind turbine (such as main shaft, bearings, impellers, gears, shaft assemblies, etc.).

[0062] It should be understood that the raw sensing signals are unprocessed sensing signals collected by the sensor array during the operation of the wind turbine to convert wind energy into electrical energy.

[0063] In practice, when the wind turbine is running, various sensors in the sensor array (such as vibration sensors, speed sensors, sound sensors, etc.) will collect raw sensing signals related to various operating states and parameters of the wind turbine from different positions and angles.

[0064] Step S20: Perform spectral analysis on the original sensing signal to determine abnormal spectral characteristics.

[0065] It should be noted that abnormal spectral characteristics can be the performance characteristics that differ from the normal operation of the wind turbine when the original sensor signal is analyzed by spectrum.

[0066] For example, under normal circumstances, the frequency spectrum of a wind turbine bearing may have a specific frequency distribution pattern. However, when a bearing fails, abnormal peaks may appear within a specific frequency range.

[0067] In practical implementation, the early warning equipment can convert the raw sensor signals of the wind turbine generators collected by the sensor array from the time domain to the frequency domain using spectrum analysis methods to obtain information on different frequency components and their intensity. Then, the information on different frequency components and their intensity is compared with the spectrum characteristics under normal conditions to obtain abnormal spectrum characteristics that deviate significantly from normal characteristics.

[0068] In one feasible implementation, step S20 of this embodiment may include the following steps: extracting the original vibration signal and the original sound signal from the original sensing signal, wherein the sensor array includes a sound sensor and a vibration sensor; performing spectral analysis on the original vibration signal using a fast Fourier transform to obtain the abnormal vibration peak value and the corresponding frequency variation characteristics of the original vibration signal; performing harmonic analysis on the original sound signal to obtain the abnormal harmonics of the original sound signal; and using the abnormal vibration peak value, the frequency variation characteristics, and the abnormal harmonics as the abnormal spectral characteristics of the original sensing signal.

[0069] It should be noted that the original sound signal can be the sound signal generated by the wind turbine during operation, collected using a sound sensor. The original vibration signal can be the vibration signal generated by the wind turbine during operation, collected using a vibration sensor.

[0070] For example, vibration sensors can be placed inside the blades and at the blade root flange mating surfaces (e.g., the vibration sensors can be installed at 1 / 3 of the blade root using adhesive bonding) to acquire blade vibration data and flange clearance data, which are then transmitted in real time to a data acquisition unit inside the hub. The acquisition unit transmits the data wirelessly via Wi-Fi to a wireless access point (AP) in the wind turbine nacelle, and then connects to the wind farm ring network via fiber optic cable within the nacelle. Finally, the wind turbine data is sent to the early warning equipment of the wind farm's wind turbine blade condition monitoring server. Thus, through vibration sensor monitoring, damage detection and early warning can be provided for wind turbine blades, including icing, lightning strike damage, surface spalling, and cracks.

[0071] For example, an acoustic sensor can be installed at the top of the tower door to collect the aerodynamic noise of the wind turbine blades during operation.

[0072] Understandably, the Fast Fourier Transform (FFT) is a fast algorithm that can perform Discrete Fourier Transform and its inverse transform on the original vibration signal. The Discrete Fourier Transform converts the discrete signal in the time domain corresponding to the original vibration signal into its frequency domain representation, thereby characterizing information such as the amplitude and phase of different frequency components contained in the signal.

[0073] The abnormal vibration peak value can be a vibration amplitude value in the original vibration signal that is significantly higher than the normal vibration amplitude during wind turbine operation. The frequency variation characteristic can be the frequency at which this abnormal vibration peak value appears in the entire original vibration signal.

[0074] It should be understood that when performing harmonic analysis on raw audio signals, the audio signal will normally exhibit regular harmonic components. Abnormal harmonics, however, are harmonic components discovered during the analysis process that deviate from the expected harmonic patterns. Examples include abnormally increased or decreased amplitudes of certain harmonics, or the appearance of harmonic frequencies that should not be present.

[0075] Specifically, the early warning equipment can extract feature values ​​from the collected raw sound signals and analyze them from multiple perspectives, including time domain, energy spectrum, and power spectrum, to determine their harmonic components. Then, the monitored harmonic components are compared with the sound signals of intact blades. By analyzing the sound signals, abnormal harmonics indicating blade damage can be identified, achieving the purpose of blade monitoring and early warning. For example, external structural damage to blades, such as leading-edge corrosion, cracking of the leading and trailing edges, blocked drainage holes, and damage and detachment of the protective film, can all be determined from the source of the sound to indicate an abnormal state.

[0076] In this embodiment, the early warning device first extracts the original vibration signal collected by the vibration sensor and the original sound signal collected by the sound sensor. Then, it performs spectral analysis on the original vibration signal using a Fast Fourier Transform to obtain the vibration amplitude values ​​that are significantly higher than the normal vibration of the wind turbine during operation, as well as the frequency characteristics of these amplitude values ​​throughout the original vibration signal. Next, it performs harmonic analysis on the original sound signal to identify abnormal harmonics indicating blade damage. Finally, the abnormal vibration peak value, frequency characteristics, and abnormal harmonics can be used as the abnormal spectral characteristics of the original sensor signals. Therefore, by analyzing the original vibration and sound signals, the accuracy of the abnormal spectral characteristics can be further improved.

[0077] In another feasible implementation, the step of performing spectral analysis on the original vibration signal using Fast Fourier Transform to obtain the abnormal vibration peak value and corresponding frequency variation characteristics of the original vibration signal includes: filtering the original vibration signal to obtain a filtered vibration signal; converting the filtered vibration signal from the time domain to the frequency domain using Fast Fourier Transform to obtain a frequency domain vibration signal; performing spectral analysis on the frequency domain vibration signal to obtain the abnormal vibration peak value; and performing time-frequency analysis based on the abnormal vibration peak value to determine the frequency variation characteristics corresponding to the abnormal vibration peak value.

[0078] In this embodiment, the early warning device first performs preprocessing such as denoising and filtering on the collected raw vibration signal to obtain a filtered vibration signal, thereby improving the quality of the raw vibration signal. Then, the filtered vibration signal is converted from a time-domain signal to a frequency-domain signal using a Fast Fourier Transform (FFT) to obtain a frequency-domain vibration signal. Next, it is checked whether abnormal peaks or characteristics appear in the filtered vibration signal within a specific frequency range. For example, a broken tooth in a wind turbine may cause a significant impact peak; if such a situation occurs, the frequency-domain vibration signal will show obvious abnormal vibration peaks. Finally, the abnormal vibration peaks are analyzed in the time and frequency dimensions using a Short-Time Fourier Transform (SFT) or Wavelet Transform to clearly capture the frequency characteristics that change over time, obtaining the frequency characteristics corresponding to the abnormal vibration peaks, thereby further improving the accuracy of the abnormal vibration data.

[0079] In another feasible implementation, the step of performing harmonic analysis on the original sound signal to obtain the abnormal harmonics of the original sound signal in this embodiment includes: performing noise reduction processing on the original sound signal to obtain a target sound signal; performing intensity measurement on the target sound signal to obtain a corresponding sound intensity value; performing harmonic analysis on the target sound signal to determine the harmonic characteristics of the target sound signal; and performing spectrum analysis on the original sound signal based on the sound intensity value and the harmonic characteristics to determine the abnormal harmonics of the original sound signal.

[0080] It should be noted that the sound intensity value can be the sound energy passing through a unit area perpendicular to the direction of sound wave propagation per unit time, and is used to represent the intensity of the sound generated by the wind turbine during operation.

[0081] Analysis of sound intensity values ​​can help determine abnormal damage to wind turbine units. For example, a sudden high-intensity sound may occur when a tooth breaks. This embodiment does not impose any restrictions on this.

[0082] In this embodiment, the early warning device can perform noise reduction processing on the original sound signal to remove interference such as environmental noise and obtain the target sound signal, thereby improving the purity of the sound signal. Then, the sound intensity of the target sound signal is measured to obtain the corresponding sound intensity value. Next, the harmonic components in the target sound signal are analyzed, and abnormal harmonics related to the fault are further extracted from the analysis results such as frequency and intensity.

[0083] Step S30: Determine the abnormal vibration region of the wind turbine based on the abnormal spectrum characteristics and the sensor array.

[0084] It should be noted that abnormal vibration areas can be any parts of the wind turbine that vibrate abnormally compared to normal conditions. This indicates problems such as malfunction, damage, imbalance, or loosening.

[0085] In practice, the early warning equipment can determine the abnormal vibration area of ​​the wind turbine from the corresponding sensor array based on the source of the abnormal spectrum characteristics.

[0086] For example, anomaly monitoring of wind turbine units may include: main bearing / main shaft, bearing failures (inner ring failure, outer ring failure, rolling element failure, cage failure, etc.), main shaft failures (shaft cracks, bending, imbalance, loose shaft components, etc.), impeller failures (blade imbalance, hub rotation and rubbing, etc.); gear failures (broken teeth, tooth surface wear, pitting, peeling, tooth surface scuffing, etc.); shaft assembly failures (shaft bending, gear eccentricity, shaft asymmetry, etc.); generator mechanical failures (generator conductor bars loosening, breakage, loosening and rubbing of internal components, foundation loosening, insufficient foundation rigidity, etc.); generator electrical failures (three-phase current imbalance, inter-turn short circuit, etc.).

[0087] Through the above monitoring, timely corrections can be made to ensure that the wind turbine operates under optimal conditions.

[0088] Step S40: Based on the abnormal vibration area, compare the abnormal spectral characteristics with a preset spectrum database to obtain the abnormal vibration value of the wind turbine. The spectrum database stores the conventional spectrum data of each component.

[0089] Step S50: Based on the abnormal vibration value of the wind turbine, issue an abnormal warning for the wind turbine.

[0090] It should be noted that the spectrum database can be a database that specifically stores the spectrum data of each component of the wind turbine under normal conditions (i.e., conventional spectrum data), reflecting the inherent characteristics of each component under normal conditions.

[0091] Understandably, abnormal vibration values ​​of wind turbines can be abnormal values ​​in which the vibration amplitude of key parts (such as nacelle, blades, main shaft, etc.) of the wind turbine exceeds the normal range during operation.

[0092] In practical implementation, the early warning equipment can compare the detected abnormal spectral characteristics with the conventional spectral data stored in the spectral database to determine the degree of abnormality in the component's operating status and obtain the abnormal vibration value of the wind turbine. Finally, based on the abnormal vibration value of the wind turbine, different levels and strategies of abnormality warnings are issued for the wind turbine, thus providing an important basis for the monitoring, maintenance, and fault diagnosis of the wind turbine.

[0093] In the technical solution provided in this embodiment, during the operation of the wind turbine, various sensors in the sensor array (such as vibration sensors, speed sensors, sound sensors, etc.) collect raw sensing signals related to various operating states and parameters of the wind turbine from different positions and angles. At this time, the early warning device can use spectral analysis to convert the raw sensing signals uploaded by the sensor array from the time domain to the frequency domain, obtaining different frequency components and their intensity information. Then, the different frequency components and their intensity information are compared with the spectral characteristics under normal conditions to obtain abnormal spectral characteristics that significantly deviate from normal characteristics. Next, based on the source of the abnormal spectral characteristics, the abnormal vibration area of ​​the wind turbine is determined from the corresponding sensor array. Then, the actually detected abnormal spectral characteristics are compared with the conventional spectral data stored in the spectral database to determine the degree of abnormality in the operating state of the components, obtaining the abnormal vibration value of the wind turbine. Finally, based on the abnormal vibration value of the wind turbine, different levels and strategies of abnormal warnings are issued for the wind turbine, thus providing an important basis for the monitoring, maintenance, and fault diagnosis of the wind turbine. Because this embodiment monitors the raw sensing signals during the operation of the wind turbine through a sensor array and performs spectral analysis on the raw sensing signals, abnormal spectral characteristics can be determined. By analyzing these abnormal spectral characteristics, the abnormal vibration regions and values ​​of wind turbines during operation can be identified. This allows for timely maintenance and repair of wind turbine units at risk of failure, providing early warning of vibration anomalies and preventing vibration-related faults, thus ensuring reliable wind turbine operation.

[0094] Based on the first embodiment described above, a second embodiment of this application is proposed. In this second embodiment, content that is the same as or similar to that in the first embodiment can be referred to the above description and will not be repeated hereafter. Based on this, please refer to... Figure 2 , Figure 2 This is a flowchart illustrating Embodiment 2 of the abnormal vibration early warning method for wind turbine generators in this application.

[0095] Step S40 in this example includes steps S41 to S43:

[0096] Step S41: Extract the normal spectrum data corresponding to the abnormal vibration region in the preset spectrum database.

[0097] Step S42: Compare the regular spectrum data with the abnormal spectrum features to obtain the corresponding frequency deviation data and amplitude change data.

[0098] It should be noted that frequency deviation data can be the deviation between regular spectrum data and anomalous spectrum features in terms of frequency. Amplitude variation data can be the degree of change between regular spectrum data and anomalous spectrum features in terms of amplitude.

[0099] Step S43: Determine the abnormal vibration value of the wind turbine based on the frequency deviation data, the amplitude change data, and the preset weight value.

[0100] It should be noted that the preset weight values ​​are pre-set in the early warning equipment to measure the weight of frequency deviation data and amplitude change data in abnormal spectrum characteristics, and thus the factors affecting wind turbine vibration. For example, in the comprehensive evaluation of abnormal wind turbine vibration values, to reflect the importance of the wind turbine in terms of vibration frequency, a preset weight value of 0.3 is given to the frequency deviation data, and a preset weight value of 0.7 is given to the amplitude change data. This can more accurately reflect the degree of influence of abnormal wind turbine vibration values ​​on the vibration frequency of the wind turbine.

[0101] In this embodiment, the early warning device can first extract the normal spectrum data corresponding to the abnormal vibration area from a preset spectrum database. Then, it compares the normal spectrum data with the abnormal spectrum characteristics to obtain the frequency deviation data and amplitude change data. Finally, different preset weight values ​​are assigned to the frequency deviation data and amplitude change data, which can more accurately reflect the influence of abnormal vibration values ​​of wind turbines on the vibration of wind turbines under different factors.

[0102] Furthermore, after step S50 in this example, the method further includes the following steps: determining whether the abnormal vibration value of the wind turbine reaches a preset threshold; when the abnormal vibration value of the wind turbine reaches the preset threshold, determining that the wind turbine has damaged components, and determining the fault type and component health of the damaged components through the abnormal vibration value of the wind turbine; generating a maintenance strategy based on the fault type, the component health, and the damaged component data; and sending the maintenance strategy to maintenance personnel so that the maintenance personnel can perform maintenance on the wind turbine according to the maintenance strategy.

[0103] It should be noted that the preset threshold can be a pre-set limit value in the early warning device to determine whether the wind turbine has been damaged. When the abnormal vibration value of the wind turbine reaches or exceeds the preset threshold, it can be determined that the vibration of the wind turbine is too severe, and a certain component of the wind turbine has been damaged (i.e., the damaged component), requiring repair.

[0104] For example, the failure type of the damaged component is the same as the failure type of the wind turbine, which may include mechanical component damage, circuit failure, control system failure, etc. It may include: bearing failure (bearing inner ring failure, outer ring failure, rolling element failure, cage failure, etc.), main shaft failure (shaft crack, bending, imbalance, loose shaft components, etc.), impeller failure, etc. This embodiment does not limit this.

[0105] Component health is an indicator that measures the degree of good condition of the aforementioned damaged components. When a damaged component fails, it exhibits a certain degree of wear and tear, etc. A series of maintenance plans (i.e., maintenance strategies) can be formulated based on its component health to ensure the normal operation and safety of the entire wind turbine unit.

[0106] In this embodiment, the early warning device can first determine whether the abnormal vibration value of the wind turbine has reached a preset threshold. If it reaches the preset threshold, it indicates that there are damaged components in the wind turbine. At this time, the fault type of the damaged component (such as problems with the mechanical transmission chain of the wind turbine main bearing, gearbox, coupling, generator, etc.) and the health of the component can be assessed by the abnormal vibration value of the wind turbine. This allows for timely proposal of maintenance strategies, enabling maintenance personnel to inspect and repair the wind turbine according to the maintenance strategies, thereby ensuring the normal operation and safety of the entire wind turbine.

[0107] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the abnormal vibration early warning method for wind turbines in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0108] This application also provides an abnormal vibration early warning device for wind turbine generators; please refer to [reference needed]. Figure 3 , Figure 3 This is a schematic diagram of the module structure of the abnormal vibration early warning device for a wind turbine according to an embodiment of this application; the abnormal vibration early warning device for the wind turbine includes:

[0109] The signal acquisition module 301 is used to acquire raw sensing signals during the operation of the wind turbine through a sensor array, wherein the sensor array is installed on various components of the wind turbine.

[0110] Spectrum analysis module 302 is used to perform spectrum analysis on the original sensing signal to determine abnormal spectrum characteristics;

[0111] The region determination module 303 is used to determine the abnormal vibration region of the wind turbine based on the abnormal spectrum characteristics and the sensor array.

[0112] The database comparison module 304 is used to compare the abnormal spectral characteristics with a preset spectrum database according to the abnormal vibration area to obtain the abnormal vibration value of the wind turbine. The spectrum database stores the conventional spectrum data of each component.

[0113] The abnormality warning module 305 is used to provide an abnormality warning for the wind turbine based on the abnormal vibration value of the wind turbine.

[0114] In one implementation, the spectrum analysis module 302 is further configured to extract the original vibration signal and the original sound signal from the original sensing signal, wherein the sensor array includes a sound sensor and a vibration sensor; perform spectrum analysis on the original vibration signal using a fast Fourier transform to obtain the abnormal vibration peak value and the corresponding frequency variation characteristics of the original vibration signal; perform harmonic analysis on the original sound signal to obtain the abnormal harmonics of the original sound signal; and use the abnormal vibration peak value, the frequency variation characteristics, and the abnormal harmonics as the abnormal spectrum characteristics of the original sensing signal.

[0115] In one implementation, the spectrum analysis module 302 is further configured to filter the original vibration signal to obtain a filtered vibration signal; convert the filtered vibration signal from the time domain to the frequency domain using a fast Fourier transform to obtain a frequency domain vibration signal; perform spectrum analysis on the frequency domain vibration signal to obtain abnormal vibration peaks; and perform time-frequency analysis based on the abnormal vibration peaks to determine the frequency variation characteristics corresponding to the abnormal vibration peaks.

[0116] In one implementation, the spectrum analysis module 302 is further configured to perform noise reduction processing on the original sound signal to obtain a target sound signal; perform intensity measurement on the target sound signal to obtain a corresponding sound intensity value; perform harmonic analysis on the target sound signal to determine the harmonic characteristics of the target sound signal; and perform spectrum analysis on the original sound signal based on the sound intensity value and the harmonic characteristics to determine the abnormal harmonics of the original sound signal.

[0117] In one implementation, the database comparison module 304 is further configured to extract the normal spectrum data corresponding to the abnormal vibration region in the preset spectrum database; compare the normal spectrum data with the abnormal spectrum features to obtain the corresponding frequency deviation data and amplitude change data; and determine the abnormal vibration value of the wind turbine based on the frequency deviation data, the amplitude change data, and the preset weight value.

[0118] In one implementation, the abnormality warning module 305 is further configured to determine whether the abnormal vibration value of the wind turbine reaches a preset threshold; when the abnormal vibration value of the wind turbine reaches the preset threshold, it is determined that there are damaged components in the wind turbine, and the fault type and component health of the damaged components are determined by the abnormal vibration value of the wind turbine; a maintenance strategy is generated based on the fault type, the component health, and the damaged component data; and the maintenance strategy is sent to maintenance personnel so that the maintenance personnel can perform maintenance on the wind turbine according to the maintenance strategy.

[0119] Other embodiments or specific implementations of the abnormal vibration early warning device for wind turbines in this application can be found in the above-described method embodiments, and will not be repeated here.

[0120] The abnormal vibration early warning device for wind turbines provided in this application employs the abnormal vibration early warning method for wind turbines described in the above embodiments. This method effectively solves the technical problem that a malfunction in any component of a wind turbine can easily lead to increased vibration and ultimately, a vibration fault, damaging the entire wind turbine. Compared to the prior art, the beneficial effects of the abnormal vibration early warning device for wind turbines provided in this application are the same as those of the abnormal vibration early warning method for wind turbines provided in the above embodiments. Furthermore, other technical features of the abnormal vibration early warning device for wind turbines are the same as those disclosed in the methods of the above embodiments, and will not be elaborated upon here.

[0121] This application provides an abnormal vibration early warning device for wind turbines. The abnormal vibration early warning device for wind turbines includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the abnormal vibration early warning method for wind turbines in the above embodiment 1.

[0122] The following is for reference. Figure 4 , Figure 4 This is a schematic diagram of the hardware operating environment involved in the abnormal vibration early warning method for wind turbines in this application embodiment. It shows a structural schematic diagram of the abnormal vibration early warning device for wind turbines suitable for implementing the abnormal vibration early warning device for wind turbines in this application embodiment. The abnormal vibration early warning device for wind turbines in this application embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The abnormal vibration early warning device for wind turbines shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0123] like Figure 4 As shown, the abnormal vibration early warning device for a wind turbine may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the abnormal vibration early warning device for the wind turbine. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the wind turbine's abnormal vibration early warning device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows an abnormal vibration early warning device for a wind turbine with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0124] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0125] The abnormal vibration early warning device for wind turbines provided in this application employs the abnormal vibration early warning method for wind turbines described in the above embodiments. This addresses the technical problem that a malfunction in any component of a wind turbine can easily lead to increased vibration and ultimately, a vibration fault, damaging the entire wind turbine. Compared to the prior art, the beneficial effects of the abnormal vibration early warning device for wind turbines provided in this application are the same as those of the abnormal vibration early warning method for wind turbines provided in the above embodiments. Furthermore, other technical features of this abnormal vibration early warning device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0126] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0127] The above description is merely a specific embodiment 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 scope of the technology 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.

[0128] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the abnormal vibration early warning method for wind turbines in the above embodiments.

[0129] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0130] The aforementioned computer-readable storage medium may be included in the abnormal vibration early warning device of the wind turbine; or it may exist independently and not be installed in the abnormal vibration early warning device of the wind turbine.

[0131] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the wind turbine abnormal vibration early warning device, the wind turbine abnormal vibration early warning device: collects raw sensing signals during the operation of the wind turbine through a sensor array installed on various components of the wind turbine; performs spectral analysis on the raw sensing signals to determine abnormal spectral characteristics; determines the abnormal vibration region of the wind turbine based on the abnormal spectral characteristics and the sensor array; compares the abnormal spectral characteristics with a preset spectral database based on the abnormal vibration region to obtain the abnormal vibration value of the wind turbine, the spectral database storing the conventional spectral data of each component; and provides an abnormal early warning for the wind turbine based on the abnormal vibration value.

[0132] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0133] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, 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 indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated 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 the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0134] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0135] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described abnormal vibration early warning method for wind turbines. This solves the technical problem that a problem in any device within a wind turbine can easily lead to increased vibration and subsequent vibration failure, thereby damaging the entire wind turbine. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the abnormal vibration early warning method for wind turbines provided in the above embodiments, and will not be repeated here.

[0136] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the abnormal vibration early warning method for wind turbines as described above.

[0137] The computer program product provided in this application can solve the technical problem that when any device in a wind turbine malfunctions, it can easily lead to increased vibration and cause vibration faults, thereby damaging the entire wind turbine. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the abnormal vibration early warning method for wind turbines provided in the above embodiments, and will not be repeated here.

[0138] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for early warning of abnormal vibration in wind turbine generators, characterized in that, The method includes: The raw sensing signals during the operation of the wind turbine are collected by a sensor array, which is installed on various components of the wind turbine. Perform spectral analysis on the original sensing signal to determine abnormal spectral characteristics; Based on the abnormal spectral characteristics and the sensor array, the abnormal vibration region of the wind turbine is determined; The abnormal spectral characteristics of the wind turbine are compared with a preset spectrum database based on the abnormal vibration region to obtain the abnormal vibration value of the wind turbine. The spectrum database stores the conventional spectrum data of each component. Based on the abnormal vibration value of the wind turbine, an abnormality warning is issued for the wind turbine. The step of performing spectral analysis on the original sensing signal to determine abnormal spectral characteristics includes: extracting the original vibration signal and the original sound signal from the original sensing signal, wherein the sensor array includes a sound sensor and a vibration sensor; performing spectral analysis on the original vibration signal using a fast Fourier transform to obtain the abnormal vibration peak value and the corresponding frequency variation characteristics of the original vibration signal; performing harmonic analysis on the original sound signal to obtain the abnormal harmonics of the original sound signal; and using the abnormal vibration peak value, the frequency variation characteristics, and the abnormal harmonics as the abnormal spectral characteristics of the original sensing signal. The step of comparing the abnormal spectral features with a preset spectrum database based on the abnormal vibration region to obtain the abnormal vibration value of the wind turbine includes: extracting the normal spectrum data corresponding to the abnormal vibration region from the preset spectrum database; comparing the normal spectrum data with the abnormal spectral features to obtain the corresponding frequency deviation data and amplitude change data; and determining the abnormal vibration value of the wind turbine based on the frequency deviation data, the amplitude change data, and a preset weight value. The step of issuing an anomaly warning for the wind turbine based on its abnormal vibration value further includes: determining whether the abnormal vibration value of the wind turbine reaches a preset threshold; when the abnormal vibration value of the wind turbine reaches the preset threshold, determining that the wind turbine has damaged components, and determining the fault type and component health of the damaged components through the abnormal vibration value; generating a maintenance strategy based on the fault type, component health, and damaged component data; and sending the maintenance strategy to maintenance personnel so that the maintenance personnel can inspect and repair the wind turbine according to the maintenance strategy.

2. The method as described in claim 1, characterized in that, The step of performing spectral analysis on the original vibration signal using Fast Fourier Transform to obtain the abnormal vibration peak value and corresponding frequency variation characteristics of the original vibration signal includes: The original vibration signal is filtered to obtain the filtered vibration signal; The filtered vibration signal is converted from the time domain to the frequency domain by a fast Fourier transform to obtain a frequency domain vibration signal. The frequency domain vibration signal was subjected to spectral analysis to obtain the abnormal vibration peak value; Time-frequency analysis is performed based on the abnormal vibration peak value to determine the frequency variation characteristics corresponding to the abnormal vibration peak value.

3. The method as described in claim 1, characterized in that, The step of performing harmonic analysis on the original sound signal to obtain the abnormal harmonics of the original sound signal includes: The original sound signal is subjected to noise reduction processing to obtain the target sound signal; The intensity of the target sound signal is measured to obtain the corresponding sound intensity value. Harmonic analysis is performed on the target sound signal to determine its harmonic characteristics; Based on the sound intensity value and the harmonic characteristics, the original sound signal is subjected to spectral analysis to determine the abnormal harmonics of the original sound signal.

4. An abnormal vibration early warning device for a wind turbine generator, characterized in that, The device performs the abnormal vibration early warning method for wind turbines as described in claim 1, and the device includes: The signal acquisition module is used to acquire raw sensing signals during the operation of the wind turbine through a sensor array, which is installed on various components of the wind turbine. The spectrum analysis module is used to perform spectrum analysis on the original sensing signal to determine abnormal spectrum characteristics; The region determination module is used to determine the abnormal vibration region of the wind turbine based on the abnormal spectrum characteristics and the sensor array. The database comparison module is used to compare the abnormal spectral characteristics with a preset spectrum database based on the abnormal vibration area to obtain the abnormal vibration value of the wind turbine. The spectrum database stores the conventional spectrum data of each component. An anomaly warning module is used to provide anomaly warnings for the wind turbine based on the abnormal vibration values ​​of the wind turbine.

5. An abnormal vibration early warning device for wind turbine generators, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the abnormal vibration early warning method for wind turbines as described in any one of claims 1 to 3.

6. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the abnormal vibration early warning method for wind turbines as described in any one of claims 1 to 3.

7. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the abnormal vibration early warning method for wind turbines as described in any one of claims 1 to 3.

Images