Wind turbine generator blade anomaly detection method and system based on vibration

Abstract

The invention discloses a vibration-based wind turbine generator blade anomaly detection method and system, and relates to the technical field of wind power. The wind turbine generator blade anomaly detection method based on vibration comprises the following steps: obtaining a sensitivity evaluation index; key feature parameter evaluation indexes are obtained; and judging whether the current vibration characteristics are abnormal or not. According to the method, the time domain analysis and the frequency domain analysis are performed on the preprocessed real-time vibration data to obtain the sensitivity evaluation index, and then whether key feature parameter extraction is executed or not is judged based on the obtained sensitivity evaluation index; and finally, comparing the obtained key characteristic parameter evaluation indexes with the vibration data reference model to judge whether the current vibration characteristics of the specified wind turbine generator blade are abnormal or not, so that the effect of improving the fault detection accuracy of the wind turbine generator blade in the vibration process is achieved. The problem of low fault detection accuracy in the vibration process of the wind turbine generator blade in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of wind power technology, and in particular to a method and system for detecting abnormality of blades of a wind turbine generator set based on vibration. Background Art

[0002] With the growing global demand for renewable energy, wind energy is playing an increasingly important role in the energy structure. As the core equipment for wind energy conversion, the operating efficiency and stability of wind turbines are crucial to the reliability and economy of energy supply. However, during the operation of wind turbines, due to the long-term complex and variable loads and environmental factors, their key components such as blades are prone to various faults, such as cracks, wear, corrosion, etc. Traditional wind turbine blade anomaly detection methods mainly rely on manual inspections and regular maintenance, which is not only time-consuming and labor-intensive, but also difficult to detect early and hidden faults. With the rapid development of sensor technology and signal processing technology, vibration-based wind turbine blade anomaly detection methods have gradually become a research hotspot.

[0003] In the prior art, sensors on the wind turbine blades are used to capture signals during blade vibration in real time and perform preprocessing to obtain vibration characteristics. The obtained vibration characteristics are then compared and analyzed with the characteristics under normal conditions to determine whether the blades are abnormal, thereby achieving accurate detection of wind turbine blade abnormalities.

[0004] For example, the invention patent with announcement number: CN118167569B announces a vibration-based wind turbine blade abnormality detection method and device, including: obtaining SCADA data and cabin vibration data of the wind turbine within a target time period; inputting the acquired data into a pre-trained blade abnormality detection model to obtain an output detection result of the blade abnormality detection model; centralizing the extracted kernel matrix to obtain a standardized kernel matrix, and performing eigenvalue decomposition on the standardized kernel matrix; determining the vibration characteristics corresponding to each modal variable based on the maximum eigenvalue obtained by decomposition and the eigenvector corresponding to the maximum eigenvalue; and determining whether the blades of the wind turbine are abnormal within the target time period based on the detection results output by the blade abnormality recognition model.

[0005] For example, a patent application with publication number CN115306650A discloses a method and system for detecting abnormal state of a wind turbine based on audio data, comprising: obtaining audio data of the wind turbine under different operating states; filtering out the audio part of a specific frequency according to the spectrogram law of the audio data; extracting the time domain features and frequency domain features of the filtered audio data, and screening the time domain features and frequency domain features; training a multi-classification model through the screened time domain features, frequency domain features and corresponding operating states to obtain a trained multi-classification model; based on the trained multi-classification model, inputting audio data to obtain an output result to realize abnormal state detection of the wind turbine.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] In the prior art, wind turbines are usually installed in outdoor environments and are affected by natural factors such as wind, rain, and lightning. These environmental factors will generate a large amount of noise signals, which interfere with the collection and analysis of blade vibration signals, thereby causing omissions or misjudgments of vibration characteristics. This leads to the problem of low accuracy in fault detection of wind turbine blades during vibration. Summary of the invention

[0008] The embodiments of the present application solve the problem of low accuracy in fault detection of wind turbine blades during vibration in the prior art by providing a vibration-based method and system for detecting abnormalities in wind turbine blades, thereby improving the accuracy of fault detection of wind turbine blades during vibration.

[0009] The embodiment of the present application provides a vibration-based wind turbine blade abnormality detection method, comprising the following steps: step one, obtaining real-time vibration data of a specified wind turbine blade under a preset working state and performing preprocessing, and performing time domain analysis and frequency domain analysis on the preprocessed real-time vibration data to obtain a sensitivity evaluation index, wherein the sensitivity evaluation index is used to evaluate the sensitivity of the vibration signal of the specified wind turbine blade to changes in the equipment state; step two, judging whether to perform key feature parameter extraction based on the obtained sensitivity evaluation index, and if the key feature parameter extraction is performed, monitoring the changes of the key feature parameters under the preset working state in real time to obtain the key feature parameter evaluation index, wherein the key feature parameter evaluation index is used to evaluate the degree of operating failure of the specified wind turbine blade at the next moment; step three, comparing the obtained key feature parameter evaluation index with the vibration data benchmark model to judge whether there is an abnormality in the current vibration characteristics of the specified wind turbine blade.

[0010] Furthermore, the time domain analysis and frequency domain analysis of the pre-processed real-time vibration data also include obtaining an environmental interference score based on the degree of influence of environmental factors on the vibration of the specified wind turbine blades, and the environmental interference score is obtained by the following method: obtaining the environmental wind speed of the area where the blades of the specified wind turbine are located at the current moment and combining the environmental wind speed influence coefficient and the maximum allowable environmental wind speed in the database to obtain the environmental wind speed influence score; obtaining the environmental wind direction of the area where the blades of the specified wind turbine are located at the current moment and combining the environmental wind direction influence coefficient and the maximum allowable environmental wind direction in the database to obtain the environmental wind direction influence score; obtaining the environmental air pressure of the area where the blades of the specified wind turbine are located at the current moment and combining the environmental air pressure influence coefficient and the maximum allowable environmental air pressure in the database to obtain the environmental air pressure influence score; obtaining a preset environmental factor weight factor from a preset database and combining the obtained environmental wind speed influence score, environmental wind direction influence score and environmental pressure influence score to obtain the environmental interference score; the environmental factor weight factor includes an environmental wind speed influence score weight factor, an environmental wind direction influence score weight factor and an environmental pressure influence score weight factor.

[0011] Furthermore, the sensitivity evaluation index is obtained by the following method: obtaining the main spectrum signal proportion score, signal-to-noise ratio and vibration signal amplitude deviation of the vibration signal of the specified wind turbine blade at the current moment, the main spectrum signal proportion score is the ratio of the main spectrum signal to the frequency domain signal, and the vibration signal amplitude deviation is the absolute value of the difference between the vibration signal amplitude at the current moment and the vibration signal amplitude at the previous moment; judging whether the vibration signal amplitude deviation is less than the reference vibration signal amplitude deviation, if so, obtaining the vibration signal amplitude deviation coefficient, otherwise prompting the operation and maintenance personnel to perform maintenance, the vibration signal amplitude deviation coefficient is the ratio of the vibration signal amplitude deviation to the reference vibration signal amplitude deviation; obtaining the phase change score of the vibration signal of the specified wind turbine blade, and combining the obtained environmental interference score, main spectrum signal proportion score, signal-to-noise ratio and vibration signal amplitude deviation coefficient to obtain the sensitivity evaluation index, the phase change score is the ratio of the absolute value of the difference between the phase at the current moment and the phase at the previous moment to the reference phase deviation.

[0012] Furthermore, the specific steps for obtaining the key characteristic parameter evaluation index are: when the obtained sensitivity evaluation index is within the sensitivity evaluation threshold range, real-time monitoring of the rotation speed of the blades of the specified wind turbine at the current moment and the output power of the specified wind turbine at the current moment; combining the rated speed and rated output power in the database to obtain the corresponding speed score and output power score, and at the same time combining the obtained sensitivity evaluation index and the environmental wind speed influence coefficient to obtain the key characteristic parameter evaluation index; the speed score is the ratio of the difference between the rated speed and the speed coefficient to the rated speed; the speed coefficient is the product of the speed and the environmental wind speed influence coefficient; the output power score is the ratio of the difference between the rated output power and the output power to the rated output power.

[0013] Furthermore, the specific limiting expression of the key characteristic parameter evaluation index is:

[0014]

[0015] Where t is the number of the current moment, t=1,2,...,T, T is the total number of the current moment, e is a natural constant, GU t It represents the key characteristic parameter evaluation index of the specified wind turbine blade at the current time t, MIN t represents the sensitivity evaluation index of the specified wind turbine blade at the current time t, ΔMIN0 represents the sensitivity evaluation threshold range, G t It represents the speed fraction of the specified wind turbine at the current time t, H t Represents the output power fraction of the specified wind turbine blade at the current time t.

[0016] The embodiment of the present application provides a vibration-based wind turbine blade abnormality detection system, including: a sensitivity evaluation index acquisition module, a key characteristic parameter evaluation index acquisition module and a current vibration feature judgment module; wherein the sensitivity evaluation index acquisition module is used to acquire real-time vibration data of a specified wind turbine blade under a preset working state and perform preprocessing, and at the same time perform time domain analysis and frequency domain analysis on the preprocessed real-time vibration data to acquire a sensitivity evaluation index, and the sensitivity evaluation index is used to evaluate the sensitivity of the vibration signal of the specified wind turbine blade to the change of the equipment state; the key characteristic parameter evaluation index acquisition module is used to determine whether to perform key characteristic parameter extraction based on the acquired sensitivity evaluation index, and if the key characteristic parameter extraction is performed, the change of the key characteristic parameters under the preset working state is monitored in real time to acquire the key characteristic parameter evaluation index, and the key characteristic parameter evaluation index is used to evaluate the degree of operating failure of the specified wind turbine blade at the next moment; the current vibration feature judgment module is used to compare the acquired key characteristic parameter evaluation index with the vibration data benchmark model to determine whether the current vibration characteristics of the specified wind turbine blade are abnormal.

[0017] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0018] 1. By performing time domain analysis and frequency domain analysis on the pre-processed real-time vibration data to obtain sensitivity evaluation indicators, and then judging whether to perform key feature parameter extraction based on the obtained sensitivity evaluation indicators, finally, the obtained key feature parameter evaluation indicators are compared with the vibration data benchmark model to determine whether there is any abnormality in the current vibration characteristics of the specified wind turbine blades, thereby achieving a more accurate judgment of the abnormal situation of the specified wind turbine blades, and then achieving an improvement in the accuracy of fault detection of the wind turbine blades during the vibration process, effectively solving the problem of low accuracy of fault detection of the wind turbine blades during the vibration process in the prior art.

[0019] 2. When the vibration signal amplitude deviation is less than the reference vibration signal amplitude deviation, the vibration signal amplitude deviation coefficient is obtained, and the sensitivity evaluation index is obtained by combining the obtained environmental interference score, main spectrum signal proportion score, signal-to-noise ratio and phase change score, thereby improving the accuracy of obtaining the sensitivity evaluation index, and further achieving a more accurate evaluation of the sensitivity of the vibration signal of the specified wind turbine blade.

[0020] 3. By real-time monitoring of the speed of the specified wind turbine blades at the current moment and the output power of the specified wind turbine blades at the current moment, the corresponding speed score and output power score are obtained by combining the rated speed and rated output power in the database, and at the same time, the key characteristic parameter evaluation index is obtained by combining the obtained sensitivity evaluation index and the environmental wind speed influence coefficient, thereby achieving an improvement in the accuracy of obtaining the key characteristic parameter evaluation index, and then achieving a more accurate evaluation of the degree of operating fault of the specified wind turbine blades at the next moment. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flow chart of a method for detecting abnormality of wind turbine blades based on vibration provided in an embodiment of the present application;

[0022] Figure 2 A schematic diagram of the structure of a wind turbine blade abnormality detection system based on vibration provided in an embodiment of the present application;

[0023] Figure 3 A flow chart for determining the current vibration characteristics provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The embodiment of the present application solves the problem of low fault detection accuracy of wind turbine blades during vibration in the prior art by providing a vibration-based wind turbine blade abnormality detection method and system. The method obtains real-time vibration data of a specified wind turbine blade under a preset working state and performs preprocessing, and performs time domain analysis and frequency domain analysis on the preprocessed real-time vibration data to obtain sensitivity evaluation indicators. Then, based on the obtained sensitivity evaluation indicators, it is determined whether to perform key feature parameter extraction. If key feature parameter extraction is performed, the changes of key feature parameters under the preset working state are monitored in real time to obtain key feature parameter evaluation indicators. Finally, the obtained key feature parameter evaluation indicators are compared with the vibration data benchmark model to determine whether there is an abnormality in the current vibration characteristics of the specified wind turbine blade, thereby improving the fault detection accuracy of the wind turbine blade during vibration.

[0025] The technical solution in the embodiment of the present application is to solve the problem of low fault detection accuracy of the blades of the wind turbine generator set during vibration. The overall idea is as follows:

[0026] Sensitivity evaluation indicators are obtained by performing time domain analysis and frequency domain analysis on the preprocessed real-time vibration data. Then, whether to perform key feature parameter extraction is determined based on the obtained sensitivity evaluation indicators. Finally, the obtained key feature parameter evaluation indicators are compared with the vibration data benchmark model to determine whether there is any abnormality in the current vibration characteristics of the specified wind turbine blades, thereby achieving the effect of improving the fault detection accuracy of the wind turbine blades during the vibration process.

[0027] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0028] like Figure 1 As shown, it is a flow chart of a vibration-based wind turbine blade abnormality detection method provided in an embodiment of the present application. The vibration-based wind turbine blade abnormality detection method provided in an embodiment of the present application includes the following steps: Step 1, obtaining real-time vibration data of a specified wind turbine blade under a preset working state and preprocessing it, and at the same time performing time domain analysis and frequency domain analysis on the preprocessed real-time vibration data to obtain a sensitivity evaluation index, and the sensitivity evaluation index is used to evaluate the sensitivity of the vibration signal of the specified wind turbine blade to changes in the equipment state; Step 2, judging whether to perform key feature parameter extraction based on the obtained sensitivity evaluation index, and if performing key feature parameter extraction, monitoring the changes of the key feature parameters under the preset working state in real time. To obtain key characteristic parameter evaluation indicators, the key characteristic parameter evaluation indicators are used to evaluate the degree of operating failure of the specified wind turbine blade at the next moment; step three, the obtained key characteristic parameter evaluation indicators are compared with the vibration data benchmark model to determine whether there is an abnormality in the current vibration characteristics of the specified wind turbine blade. The vibration data benchmark model is established by deeply analyzing the preprocessed real-time vibration data through the principal component analysis method. The real-time vibration data is used to reflect the real-time vibration state of the specified wind turbine blade at the current moment. The vibration data benchmark model is used to visualize (visualize through the vibration data-time curve image) the vibration characteristics of the specified wind turbine blade under the preset working state, and the vibration characteristics include a normal vibration range and an abnormal vibration mode.

[0029] Among them, real-time vibration data includes vibration data and environmental data; vibration data (monitored in real time through a vibration data collector, such as the SZ-BSZ602 / 903 vibration data collector) includes vibration acceleration, vibration displacement, vibration velocity, vibration frequency, vibration phase and vibration amplitude; environmental data includes ambient wind speed (measured by an anemometer), ambient wind direction (measured by anemometer) and ambient air pressure (measured by a barometer); key characteristic parameters include time domain characteristic data and frequency domain characteristic data; time domain characteristic data include average vibration amplitude, average vibration frequency and average vibration phase; frequency domain characteristic data include main frequency band position and spectrum entropy.

[0030] In this embodiment, the specific steps of preprocessing the real-time vibration data are as follows: using the real-time vibration data as the input signal of the adaptive filter, dynamically adjusting the parameters of the filter (such as the filter order) by using the least mean square error (LMS) algorithm in the adaptive filtering algorithm to minimize the noise component in the output signal, and monitoring the performance of the filter in real time, such as the signal-to-noise ratio (SNR) or mean square error (MSE) of the output signal. The preprocessed real-time vibration data (i.e., the output signal of the adaptive filter) has a higher signal-to-noise ratio than the input signal, which helps to improve the signal-to-noise ratio and availability of the vibration signal of the blade of a specified wind turbine.

[0031] Specifically, the specific steps for establishing the vibration data benchmark model are as follows: organize the preprocessed vibration data into a data matrix, in which each row represents an observation value (such as vibration data at a time point), and each column represents a variable (such as different vibration characteristics). After data standardization, calculate the correlation coefficient matrix of the data matrix to understand the correlation between the variables, and then calculate its eigenvalues ​​and eigenvectors based on the correlation coefficient matrix, sort the eigenvalues ​​from large to small, and select the principal components corresponding to the eigenvalues ​​greater than the preset eigenvalues ​​(set by the preset personnel) as the new comprehensive indicators. Finally, construct the principal component matrix based on the selected principal components and the corresponding eigenvectors, that is, project the original data onto the selected principal components to obtain the vibration data benchmark model.

[0032] Among them, the eigenvalue represents the variance contribution rate of the principal component, that is, the explanatory power of each principal component on the data, and the eigenvector represents the direction of the principal component, that is, the projection of the original data on each principal component; the number of principal components can be determined according to the actual situation, and generally the principal components with a cumulative contribution rate of more than 85% can be selected to ensure less information loss. A more accurate judgment of the vibration characteristics of the blades of a specified wind turbine under a preset working state is achieved.

[0033] Further, the pre-processed real-time vibration data is subjected to time domain analysis and frequency domain analysis, which also includes obtaining an environmental interference score according to the influence of environmental factors on the vibration of the blades of the specified wind turbine, and the environmental interference score is obtained by the following method: obtaining the environmental wind speed of the area where the blades of the specified wind turbine are located at the current moment and combining the environmental wind speed influence coefficient in the database and the maximum allowable environmental wind speed to obtain the environmental wind speed influence score (that is, S in the limiting expression of the environmental interference score) t ); obtain the ambient wind direction of the area where the blades of the specified wind turbine are located at the current moment and combine the ambient wind direction influence coefficient and the maximum allowable ambient wind direction in the database to obtain the ambient wind direction influence score (i.e., the X in the limiting expression of the ambient interference score) t); obtain the ambient air pressure of the area where the blades of the specified wind turbine are located at the current moment and combine the ambient air pressure influence coefficient and the maximum allowable ambient air pressure in the database to obtain the ambient air pressure influence score (that is, Y in the limiting expression of the environmental interference score) t ); obtain a preset environmental factor weight factor from a preset database and combine the obtained environmental wind speed impact score, environmental wind direction impact score and environmental pressure impact score to obtain an environmental interference score.

[0034] Among them, the ambient wind speed impact score is the ratio of the product of the ambient wind speed and the ambient wind speed impact coefficient to the maximum allowable ambient wind speed; the ambient wind direction impact score is the ratio of the product of the sine value of the ambient wind direction (between 30° and 60°) and the ambient wind direction impact coefficient to the sine value of the maximum allowable ambient wind direction; the ambient air pressure impact score is the ratio of the product of the ambient air pressure and the ambient air pressure impact coefficient to the maximum allowable ambient air pressure; the environmental factor weight factors include the ambient wind speed impact score weight factor, the ambient wind direction impact score weight factor and the ambient air pressure impact score weight factor.

[0035] In this embodiment, the specific limiting expression of the environmental interference score is:

[0036] RAO t =log2(β1*S t +β2*X t +β3*Y t +1);

[0037]

[0038] Where t is the number at the current moment, t=1,2,...,T, T is the total number at the current moment, RAO t represents the environmental interference score of the specified wind turbine blade at the current time t, β1 represents the weight factor of the environmental wind speed impact score, S t represents the environmental wind speed impact score of the specified wind turbine blade at the current time t, α1 represents the environmental wind speed impact coefficient, S1 t represents the ambient wind speed of the blades of the specified wind turbine at the current time t, S1 max represents the maximum allowable ambient wind speed, β2 represents the weight factor of the ambient wind direction, and X t represents the environmental wind direction impact score of the specified wind turbine blade at the current time t, α2 represents the environmental wind direction impact coefficient, X1 t Indicates the ambient wind direction of the blades of the specified wind turbine at the current time t, X1 max represents the maximum allowable environmental wind direction, β3 represents the weight factor of the environmental air pressure impact score, and Y trepresents the ambient air pressure impact fraction of the specified wind turbine blade at the current time t, α3 represents the ambient air pressure impact coefficient, Y1 t represents the ambient air pressure of the specified wind turbine blade at the current time t, Y1 max Indicates the maximum allowable ambient air pressure.

[0039] Specifically, the maximum allowable ambient wind speed is the maximum value of the historical ambient wind speed of the area where the blades of the specified wind turbine are located in the preset database, the maximum allowable ambient wind direction is the maximum value of the historical ambient wind direction of the area where the blades of the specified wind turbine are located in the preset database, and the maximum allowable ambient air pressure is the maximum value of the historical ambient air pressure of the area where the blades of the specified wind turbine are located in the preset database.

[0040] In this example, the weight factor of the environmental wind speed impact score, the weight factor of the environmental wind direction impact score, and the weight factor of the environmental pressure impact score are respectively the influence of the environmental wind speed impact score, the environmental wind direction impact score, and the environmental pressure impact score preset in the preset database on the vibration of the blades of the specified wind turbine. Specifically, the preset database stores the preset weight factors corresponding to the environmental wind speed impact score, the environmental wind direction impact score, and the environmental pressure impact score. There is a preset mapping relationship between these weight factors and the environmental wind speed impact score, the environmental wind direction impact score, and the environmental pressure impact score. This mapping relationship can be one-to-one or many-to-one. In practical applications, the real-time environmental wind speed impact score, the environmental wind direction impact score, and the environmental pressure impact score can be input into this mapping relationship, so as to quickly obtain the corresponding weight factors, which provides an important quantitative indicator for evaluating the environmental interference to the vibration of the wind turbine blades, and then more accurately calculates the environmental interference score. The value range of these weight factors is limited to between 0 and 1, which ensures their rationality and effectiveness in calculating the environmental interference score.

[0041] It should be understood that the environmental interference score increases with the increase of the environmental wind speed impact score, the environmental wind direction impact score and the environmental air pressure impact score, among which the environmental wind speed impact score increases with the increase of the environmental wind speed, the environmental wind direction impact score increases with the increase of the environmental wind direction, and the environmental air pressure impact score increases with the increase of the environmental air pressure.

[0042] It should be noted that the environmental wind direction impact score also indirectly affects the values ​​of the environmental wind speed impact score and the environmental air pressure impact score. When the environmental wind direction increases, the angle between the environmental wind direction and the blade plane becomes larger, and the corresponding environmental wind speed impact score decreases. Suppose in a valley, if the environmental wind direction blows from one side of the valley to the other, then a high-pressure area may form on one side of the valley and a low-pressure area on the other side. This pressure change may affect the air flow around the wind turbine blades, and thus affect the environmental air pressure impact score.

[0043] In this example, the environmental wind direction impact score indirectly affects the values ​​of environmental wind speed and ambient air pressure in fault detection through interaction with them, which helps to comprehensively analyze the influence of environmental factors on the vibration characteristics of the blades of a specified generator set, thereby improving the accuracy of fault detection of wind turbine blades during vibration, and effectively solving the problem of low accuracy of fault detection of wind turbine blades during vibration in the prior art.

[0044] It should be added that the environmental interference score is obtained, and then the time domain analysis and frequency domain analysis are determined based on the obtained environmental interference score. The specific judgment process is: determine whether the obtained environmental interference score is within the allowable range of environmental interference (excluding the maximum and minimum values ​​of the historical environmental interference scores). If so, it indicates that the influence of environmental factors on the vibration of the blades of the specified wind turbine is within the allowable range. At this time, time domain analysis and frequency domain analysis are performed. Otherwise, it indicates that the influence of environmental factors on the vibration of the blades of the specified wind turbine is not within the allowable range. At this time, time domain analysis and frequency domain analysis are not performed and the operation and maintenance personnel are prompted to immediately initiate the emergency plan.

[0045] Among them, the allowable range of environmental interference represents the range corresponding to the maximum and minimum values ​​of the historical environmental interference scores in the working area where the blades of the specified wind turbine are located in the preset database. When the obtained environmental interference score is not within the allowable range of environmental interference, the operation and maintenance personnel need to be prompted to take emergency shutdown measures (such as twisting the emergency brake button of the specified wind turbine), thereby achieving safe and stable operation of the specified wind turbine, and further achieving a more accurate evaluation of the vibration characteristics of the blades of the specified wind turbine.

[0046] Furthermore, the specific steps of performing time domain analysis (used to reflect the characteristics of the waveform, amplitude and phase of the vibration signal of the blade of the specified wind turbine set changing with time) and frequency domain analysis (used to reflect the amplitude and phase corresponding to the frequency components in the vibration signal of the blade of the specified wind turbine set) on the pre-processed real-time vibration data include: real-time monitoring of the changes in the mean, variance, peak value and root mean square value corresponding to the vibration data within the vibration period of the specified wind turbine set blade; real-time monitoring of the distribution characteristics of the vibration data in the frequency domain, and converting the time domain signal in the vibration signal into a frequency domain signal through fast Fourier transform.

[0047] In this embodiment, the frequency domain signal includes a main spectrum signal and a sub-spectrum signal; the main spectrum signal (directly reflecting the vibration condition of the blades of the specified wind turbine generator set under normal working conditions) is used to reflect the natural frequency of the blades of the specified wind turbine generator set (the unattenuated periodic oscillation frequency generated when receiving an external excitation signal without damping); the sub-spectrum signal (directly reflecting the unbalanced vibration condition of the blades of the specified wind turbine generator set under normal working conditions) is used to reflect the noise frequency of the blades of the specified wind turbine generator set.

[0048] It should be noted that for wind turbine blades, their natural frequency is determined by the physical properties of the blades themselves (such as mass and stiffness), and is the basic frequency of the blades during free vibration. In frequency domain analysis, the main spectrum signal directly reflects this natural frequency, which reflects the main vibration characteristics of the blades under normal working conditions. In fault detection, by analyzing the main spectrum signal, it can be determined whether the blades have abnormal vibrations, and then whether they are in normal working conditions.

[0049] Furthermore, the sensitivity evaluation index is obtained by the following method: when the obtained environmental interference score is within the allowable range of environmental interference, the main spectrum signal proportion score of the vibration signal of the specified wind turbine blade at the current moment is obtained (that is, B in the restriction expression of the sensitivity evaluation index). t ), signal-to-noise ratio (i.e., N in the limiting expression of the sensitivity evaluation index t ) and the vibration signal amplitude deviation, the main spectrum signal proportion fraction is the ratio of the main spectrum signal to the frequency domain signal, the signal-to-noise ratio is the ratio of the effective signal to the noise signal in the vibration signal, and the vibration signal amplitude deviation is the absolute value of the difference between the vibration signal amplitude at the current moment and the vibration signal amplitude at the previous moment; determine whether the vibration signal amplitude deviation is less than the reference vibration signal amplitude deviation, and if so, obtain the vibration signal amplitude deviation coefficient (that is, P in the restriction expression of the sensitivity evaluation index) t ), otherwise it is considered that the waveform of the vibration signal is distorted and the operation and maintenance personnel are prompted to perform maintenance. When it is not 1 at the current moment, the vibration signal amplitude deviation coefficient is the ratio of the vibration signal amplitude deviation to the reference vibration signal amplitude deviation. When it is 1 at the current moment, the vibration signal amplitude deviation coefficient is the ratio of the vibration signal amplitude to the reference vibration signal amplitude deviation (at this time, the vibration signal amplitude at the previous moment is 0); obtain the phase change score of the vibration signal of the specified wind turbine blade (that is, Q in the restriction expression of the sensitivity evaluation index t ), and combined with the obtained environmental interference score, main spectrum signal proportion score, signal-to-noise ratio and vibration signal amplitude deviation coefficient, the sensitivity evaluation index is obtained. When the current moment is not 1, the phase change score is the ratio of the absolute value of the difference between the phase at the current moment and the phase at the previous moment to the reference phase deviation. When the current moment is 1, the phase change score is the ratio of the phase at the current moment to the reference phase deviation (the phase at the previous moment is 0 at this time).

[0050] In this embodiment, the specific limiting expression of the sensitivity evaluation index is:

[0051]

[0052] Where t is the number of the current moment, t=1,2,...,T, T is the total number of the current moment, e is a natural constant, MIN t It represents the sensitivity evaluation index of the specified wind turbine blade at the current time t, RAO t represents the environmental interference score of the specified wind turbine blade at the current time t, ΔRAO0 represents the allowable range of environmental interference, B t Indicates the proportion of the main spectrum signal of the specified wind turbine blade at the current time t, B2 t represents the main spectrum signal of the blade of the specified wind turbine at the current time t, B1 t represents the frequency domain signal of the blade of a specified wind turbine at the current time t, N t represents the signal-to-noise ratio of the blade of a specified wind turbine at the current time t, N2 t Indicates the effective signal of the blade of the specified wind turbine at the current time t, N1 t represents the noise signal of the blade of a specified wind turbine at the current time t, P t P1 represents the vibration signal amplitude deviation coefficient of the specified wind turbine blade at the current time t. t represents the vibration signal amplitude of the specified wind turbine blade at the current time t, P1 t-1 represents the vibration signal amplitude of the specified wind turbine blade at the previous time t-1, ΔP10 represents the reference vibration signal amplitude deviation, Q t represents the phase change fraction of the specified wind turbine blade at the current time t, Q1 t represents the phase of the blades of a specified wind turbine at the current time t, Q1 t-1 represents the phase of the blade of the specified wind turbine at the previous time t-1, and ΔQ10 represents the reference phase deviation.

[0053] Specifically, the vibration signal amplitude is the highest peak of the vibration waveform (displayed by an oscilloscope) corresponding to the vibration signal generated by the specified wind turbine blade during the vibration process, the reference vibration signal amplitude deviation is represented by the sum and average of the historical vibration signal amplitude deviations of the specified wind turbine blade in the historical vibration process in the preset database, and the reference phase deviation is represented by the sum and average of the historical phase deviations of the specified wind turbine blade in the historical vibration process in the preset database.

[0054] It should be understood that when the current moment t is 1 and the previous moment is 0, the corresponding vibration signal amplitude and phase are both 0; when the current moment t is not 1, the sensitivity evaluation index decreases with the increase of the environmental interference score, and increases with the increase of the vibration signal amplitude deviation coefficient, the phase change score, the main spectrum signal proportion score and the signal-to-noise ratio. Among them, the phase change score also indirectly affects the value of the main spectrum signal proportion score. When the phase deviation increases, it may cause the signal to be more dispersed in the frequency domain, and the proportion of the main spectrum signal will be relatively reduced (that is, the main spectrum signal proportion score will decrease). On the contrary, if the phase deviation is small, the signal distribution in the frequency domain may be more concentrated, and the proportion of the main spectrum signal will be relatively increased (that is, the main spectrum signal proportion score will increase).

[0055] Therefore, the phase change score indirectly affects the proportion of the main spectrum signal by affecting the distribution of the signal in the frequency domain. By considering the above indirect influence mechanism, the vibration state of the wind turbine blades can be evaluated more accurately, thereby achieving improved accuracy in fault detection of the wind turbine blades during vibration, and effectively solving the problem of low accuracy in fault detection of the wind turbine blades during vibration in the prior art.

[0056] Furthermore, the specific process of judging whether to execute key feature parameter extraction based on the obtained sensitivity evaluation index is as follows: judging whether the obtained sensitivity evaluation index is within the sensitivity evaluation threshold range: if the obtained sensitivity evaluation index is within the sensitivity evaluation threshold range (excluding the maximum and minimum values ​​equal to the historical sensitivity evaluation index), it indicates that the vibration signal of the specified wind turbine blade meets the sensitivity requirements for equipment state changes and key feature parameter extraction is executed; if the obtained sensitivity evaluation index is not within the sensitivity evaluation threshold range, it indicates that the vibration signal of the specified wind turbine blade does not meet the sensitivity requirements for equipment state changes. At this time, key feature parameter extraction is not executed and the sensors deployed on the specified wind turbine blades are recalibrated.

[0057] In this embodiment, the sensitivity evaluation threshold range represents the range corresponding to the maximum and minimum values ​​of the historical sensitivity evaluation index of the specified wind turbine blade in the preset database during the historical operation process. Through real-time monitoring and judgment of the sensitivity evaluation index, this example can promptly detect signs of potential faults and take corresponding measures to prevent them, which helps to reduce the chance of failure and improve the stability and reliability of the system.

[0058] Furthermore, the specific steps for obtaining the key characteristic parameter evaluation index are as follows: when the obtained sensitivity evaluation index is within the sensitivity evaluation threshold range, real-time monitoring of the speed of the blades of the specified wind turbine at the current moment and the output power of the specified wind turbine at the current moment; combining the rated speed and rated output power in the database to obtain the corresponding speed score (i.e., G in the restriction expression of the key characteristic parameter evaluation index); t ) and the output power fraction (i.e., H in the limiting expression of the key characteristic parameter evaluation index) t ), and at the same time combined with the obtained sensitivity evaluation index (i.e., MIN in the restriction expression of the key characteristic parameter evaluation index t ) and the environmental wind speed influence coefficient (i.e., α1 in the restriction expression of the key characteristic parameter evaluation index) to obtain the key characteristic parameter evaluation index.

[0059] Among them, the speed score is the ratio of the difference between the rated speed (set by the designated wind turbine manufacturer) and the speed coefficient to the rated speed; the speed coefficient is the product of the speed (measured by the speed sensor) and the ambient wind speed influence coefficient; the output power score is the ratio of the difference between the rated output power (set by the designated wind turbine manufacturer) and the output power (measured by the power sensor) to the rated output power.

[0060] Assuming that the sensitivity evaluation threshold range is between 0.8 and 1.2, the specific limiting expression of the key characteristic parameter evaluation index is:

[0061]

[0062]

[0063] Where t is the number of the current moment, t=1,2,...,T, T is the total number of the current moment, e is a natural constant, GU t It represents the key characteristic parameter evaluation index of the specified wind turbine blade at the current time t, MIN t represents the sensitivity evaluation index of the specified wind turbine blade at the current time t, ΔMIN0 represents the sensitivity evaluation threshold range, G t Indicates the speed fraction of the specified wind turbine at the current time t, G10 represents the rated speed, G1 t represents the speed of the specified wind turbine at the current time t, α1 represents the environmental wind speed influence coefficient, H t It represents the output power fraction of the specified wind turbine blade at the current time t, H10 represents the rated output power, H1 t Represents the output power of the specified wind turbine blade at the current time t.

[0064] In this embodiment, the statistical table of changes in the key characteristic parameter evaluation index is shown in Table 1, and the corresponding sensitivity evaluation threshold range is 0.8 to 1.2:

[0065] Table 1 Statistics of changes in key characteristic parameter evaluation indicators

[0066]

[0067] It should be understood that, as shown in Table 1, the key characteristic parameter evaluation index decreases with the increase of the sensitivity evaluation index, and increases with the increase of the speed score and the output power score, among which the speed score decreases with the increase of the speed, and the output power score decreases with the increase of the output power.

[0068] It should be noted that the speed fraction also indirectly affects the value of the output power fraction. When the speed increases, the specified wind turbine can capture more wind energy and convert it into electrical energy. The corresponding speed fraction decreases, and the output power may increase (because more wind energy is captured), that is, the output power fraction decreases. By considering the above-mentioned indirect influence mechanism, the accuracy and reliability of fault detection during the vibration of the blades of the specified wind turbine can be effectively improved, thereby achieving an improvement in the accuracy of fault detection of the wind turbine blades during the vibration process, and effectively solving the problem of low accuracy of fault detection of the wind turbine blades during the vibration process in the prior art.

[0069] Furthermore, the specific process of comparing the obtained key characteristic parameter evaluation index with the vibration data benchmark model to determine whether the current vibration characteristics of the specified wind turbine blade are abnormal is as follows: determine whether the obtained key characteristic parameter evaluation index is within the key characteristic parameter evaluation threshold range: if the obtained key characteristic parameter evaluation index is within the key characteristic parameter evaluation threshold range (excluding the maximum and minimum values ​​equal to the historical key characteristic parameter evaluation index), it indicates that the current vibration characteristics of the specified wind turbine blade are within the normal vibration range in the vibration characteristics (that is, the specified wind turbine blade does not have an operating fault at the current moment); if the obtained key characteristic parameter evaluation index is not within the key characteristic parameter evaluation threshold range, it indicates that the current vibration characteristics of the specified wind turbine blade are not within the normal vibration range in the vibration characteristics (that is, the specified wind turbine blade has an operating fault at the current moment), and at this time, critical abnormality levels are divided and the operation and maintenance personnel are prompted to perform maintenance.

[0070] In this embodiment, the key characteristic parameter evaluation threshold range (set by the preset personnel) represents the range corresponding to the maximum and minimum values ​​of the historical key characteristic parameter evaluation indicators of the specified wind turbine blades in the preset database; the critical abnormality level includes the first critical abnormality and the second critical abnormality; the first critical abnormality indicates that the key characteristic parameter evaluation indicator obtained is not less than the maximum value of the historical key characteristic parameter evaluation indicator; the second critical abnormality indicates that the key characteristic parameter evaluation indicator obtained is not greater than the minimum value of the historical key characteristic parameter evaluation indicator.

[0071] In this example, the system can classify critical abnormality levels according to the abnormality degree of key characteristic parameter evaluation indicators, and provide targeted maintenance suggestions for operation and maintenance personnel, thereby improving maintenance efficiency and accuracy. Secondly, by real-time monitoring and judging the vibration state of wind turbine blades, abnormal situations can be discovered and handled in a timely manner, which helps to reduce the downtime of wind turbines and thus improve the overall performance and reliability of the system.

[0072] like Figure 2 As shown, it is a structural schematic diagram of a vibration-based wind turbine blade abnormality detection system provided in an embodiment of the present application. The vibration-based wind turbine blade abnormality detection system provided in an embodiment of the present application includes: a sensitivity evaluation index acquisition module, a key characteristic parameter evaluation index acquisition module and a current vibration characteristic judgment module; wherein the sensitivity evaluation index acquisition module is used to obtain the real-time vibration data of the specified wind turbine blade under a preset working state and perform preprocessing, and at the same time perform time domain analysis and frequency domain analysis on the preprocessed real-time vibration data to obtain a sensitivity evaluation index, and the sensitivity evaluation index is used to evaluate the sensitivity of the vibration signal of the specified wind turbine blade to the change of the equipment state; the key characteristic parameter evaluation index acquisition module is used to judge whether to perform key characteristic parameter extraction based on the acquired sensitivity evaluation index, If key feature parameter extraction is performed, the changes of key feature parameters under the preset working state are monitored in real time to obtain key feature parameter evaluation indicators, which are used to evaluate the degree of operating failure of the specified wind turbine blade at the next moment; the current vibration feature judgment module is used to compare the acquired key feature parameter evaluation indicators with the vibration data benchmark model to determine whether there is an abnormality in the current vibration characteristics of the specified wind turbine blade. The vibration data benchmark model is established by performing an in-depth analysis of the preprocessed real-time vibration data through the principal component analysis method. The real-time vibration data is used to reflect the real-time vibration state of the specified wind turbine blade at the current moment. The vibration data benchmark model is used to visualize the vibration characteristics of the specified wind turbine blade under the preset working state, and the vibration characteristics include a normal vibration range and an abnormal vibration mode.

[0073] like Figure 3As shown, it is a flow chart for judging the current vibration characteristics provided in an embodiment of the present application. This process not only improves the accuracy and efficiency of abnormal detection of wind turbine blades, but also can evaluate the operating status of the blades in real time based on vibration data, timely discover and warn of potential faults, and provide strong technical support for the operation and maintenance management of wind farms.

[0074] To summarize, the embodiment of the present application performs time domain analysis and frequency domain analysis on the preprocessed real-time vibration data to obtain sensitivity evaluation indicators, and then determines whether to perform key feature parameter extraction based on the obtained sensitivity evaluation indicators. Finally, the obtained key feature parameter evaluation indicators are compared with the vibration data benchmark model to determine whether there is any abnormality in the current vibration characteristics of the specified wind turbine blades, thereby achieving a more accurate judgment of the abnormal conditions of the specified wind turbine blades, and further achieving an improvement in the fault detection accuracy of the wind turbine blades during the vibration process, effectively solving the problem of low fault detection accuracy of the wind turbine blades during the vibration process in the prior art.

[0075] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0077] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0078] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0079] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0080] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for detecting abnormality of wind turbine blades based on vibration, characterized in that: The following steps are involved: Step 1: obtaining real-time vibration data of a blade of a specified wind turbine in a preset working state and performing preprocessing, and performing time domain analysis and frequency domain analysis on the preprocessed real-time vibration data to obtain a sensitivity evaluation index, wherein the sensitivity evaluation index is used to evaluate the sensitivity of the vibration signal of the blade of the specified wind turbine to changes in the equipment state; Step 2: judging whether to perform key characteristic parameter extraction based on the obtained sensitivity evaluation index; if the key characteristic parameter extraction is performed, monitoring the changes of the key characteristic parameters under the preset working state in real time to obtain the key characteristic parameter evaluation index, which is used to evaluate the operating fault degree of the blade of the specified wind turbine at the next moment; Step three, compare the obtained key characteristic parameter evaluation index with the vibration data benchmark model to determine whether the current vibration characteristics of the specified wind turbine blade are abnormal.

2. A vibration-based wind turbine blade abnormality detection method as claimed in claim 1, characterized in that: The real-time vibration data includes vibration data and environmental data; The vibration data includes vibration acceleration, vibration displacement, vibration velocity, vibration frequency, vibration phase and vibration amplitude; The environmental data includes environmental wind speed, environmental wind direction and environmental air pressure; The key characteristic parameters include time domain characteristic data and frequency domain characteristic data; The time domain characteristic data includes average vibration amplitude, average vibration frequency and average vibration phase; The frequency domain feature data includes the main frequency band position and spectrum entropy.

3. A vibration-based wind turbine blade abnormality detection method as claimed in claim 1, characterized in that: The time domain analysis and frequency domain analysis of the pre-processed real-time vibration data also include obtaining an environmental interference score according to the influence of environmental factors on the vibration of the blades of a specified wind turbine, and the environmental interference score is obtained by the following method: Obtain the ambient wind speed of the area where the blades of the specified wind turbine are located at the current moment and obtain the ambient wind speed impact score by combining the ambient wind speed impact coefficient and the maximum allowable ambient wind speed in the database; Obtain the ambient wind direction of the area where the blades of the specified wind turbine are located at the current moment and obtain the ambient wind direction impact score by combining the ambient wind direction impact coefficient and the maximum allowable ambient wind direction in the database; Obtain the ambient air pressure of the area where the blades of the specified wind turbine are located at the current moment and obtain the ambient air pressure impact score by combining the ambient air pressure impact coefficient and the maximum allowable ambient air pressure in the database; Obtaining a preset environmental factor weight factor from a preset database and combining the obtained environmental wind speed impact score, environmental wind direction impact score and environmental air pressure impact score to obtain an environmental interference score; The environmental factor weight factors include an environmental wind speed influence score weight factor, an environmental wind direction influence score weight factor and an environmental air pressure influence score weight factor.

4. A vibration-based wind turbine blade abnormality detection method as claimed in claim 1, characterized in that: The specific steps of performing time domain analysis and frequency domain analysis on the pre-processed real-time vibration data include: Real-time monitoring of the changes in the mean, variance, peak value and RMS value corresponding to the vibration data within the vibration cycle of the specified wind turbine blade; Monitor the distribution characteristics of vibration data in the frequency domain in real time, and convert the time domain signal in the vibration signal into the frequency domain signal through fast Fourier transform; The frequency domain signal includes a primary spectrum signal and a secondary spectrum signal; The main spectrum signal is used to reflect the natural frequency of the blade of the specified wind turbine; The sub-spectrum signal is used to reflect the noise frequency of the blades of a specified wind turbine generator set.

5. A vibration-based wind turbine blade abnormality detection method as claimed in claim 1, characterized in that: The sensitivity evaluation index is obtained by the following method: Obtain the main spectrum signal proportion fraction, signal-to-noise ratio and vibration signal amplitude deviation of the vibration signal of the specified wind turbine blade at the current moment, wherein the main spectrum signal proportion fraction is the ratio of the main spectrum signal to the frequency domain signal, and the vibration signal amplitude deviation is the absolute value of the difference between the vibration signal amplitude at the current moment and the vibration signal amplitude at the previous moment; Determine whether the vibration signal amplitude deviation is less than the reference vibration signal amplitude deviation. If so, obtain the vibration signal amplitude deviation coefficient. Otherwise, prompt the operation and maintenance personnel to perform maintenance. The vibration signal amplitude deviation coefficient is the ratio of the vibration signal amplitude deviation to the reference vibration signal amplitude deviation. The phase change score of the vibration signal of the specified wind turbine blade is obtained, and the sensitivity evaluation index is obtained by combining the obtained environmental interference score, the main spectrum signal proportion score, the signal-to-noise ratio and the vibration signal amplitude deviation coefficient. The phase change score is the ratio of the absolute value of the difference between the phase at the current moment and the phase at the previous moment to the reference phase deviation.

6. A vibration-based wind turbine blade abnormality detection method as claimed in claim 1, characterized in that: The specific process of judging whether to perform key feature parameter extraction based on the acquired sensitivity evaluation index is as follows: Determine whether the obtained sensitivity evaluation index is within the sensitivity evaluation threshold range: If the obtained sensitivity evaluation index is within the sensitivity evaluation threshold range, key feature parameter extraction is performed; If the obtained sensitivity evaluation index is not within the sensitivity evaluation threshold range, the key characteristic parameter extraction is not performed and the sensors deployed on the blades of the specified wind turbine are recalibrated.

7. A vibration-based wind turbine blade abnormality detection method as claimed in claim 1, characterized in that: The specific steps for obtaining the key characteristic parameter evaluation index are as follows: Real-time monitoring of the speed of the blades of a specified wind turbine at the current moment and the output power of the specified wind turbine at the current moment; Combine the rated speed and rated output power in the database to obtain the corresponding speed score and output power score, and combine the obtained sensitivity evaluation index and environmental wind speed influence coefficient to obtain the key characteristic parameter evaluation index; The speed fraction is the ratio of the difference between the rated speed and the speed coefficient to the rated speed; The rotation speed coefficient is the product of the rotation speed and the environmental wind speed influence coefficient; The output power fraction is a ratio of a difference between the rated output power and the output power to the rated output power.

8. A vibration-based wind turbine blade abnormality detection method as claimed in claim 7, characterized in that: The specific limiting expression of the key characteristic parameter evaluation index is: Where t is the number of the current moment, t=1,2,...,T, T is the total number of the current moment, e is a natural constant, GU t It represents the key characteristic parameter evaluation index of the specified wind turbine blade at the current time t, MIN t represents the sensitivity evaluation index of the specified wind turbine blade at the current time t, ΔMIN0 represents the sensitivity evaluation threshold range, G t It represents the speed fraction of the specified wind turbine at the current time t, H t Represents the output power fraction of the specified wind turbine blade at the current time t.

9. A vibration-based wind turbine blade abnormality detection method as claimed in claim 1, characterized in that: The specific process of comparing the obtained key characteristic parameter evaluation index with the vibration data benchmark model to determine whether the current vibration characteristics of the specified wind turbine blade are abnormal is as follows: Determine whether the obtained key feature parameter evaluation indicators are within the key feature parameter evaluation threshold range: If the key characteristic parameter evaluation index obtained is within the key characteristic parameter evaluation threshold range, it indicates that the current vibration characteristics of the blade of the specified wind turbine are within the normal vibration range of the vibration characteristics; If the key characteristic parameter evaluation index obtained is not within the key characteristic parameter evaluation threshold range, a critical abnormality level is classified and the operation and maintenance personnel are prompted to perform maintenance; The critical abnormality level includes a first critical abnormality and a second critical abnormality.

10. A wind turbine blade abnormality detection system based on vibration, characterized in that: include: Sensitivity evaluation index acquisition module, key characteristic parameter evaluation index acquisition module and current vibration characteristic judgment module; The sensitivity evaluation index acquisition module is used to acquire the real-time vibration data of the blades of the specified wind turbine in a preset working state and perform preprocessing, and at the same time perform time domain analysis and frequency domain analysis on the preprocessed real-time vibration data to obtain the sensitivity evaluation index, and the sensitivity evaluation index is used to evaluate the sensitivity of the vibration signal of the blades of the specified wind turbine to the change of the equipment state; The key characteristic parameter evaluation index acquisition module is used to determine whether to perform key characteristic parameter extraction based on the acquired sensitivity evaluation index. If the key characteristic parameter extraction is performed, the change of the key characteristic parameter under the preset working state is monitored in real time to obtain the key characteristic parameter evaluation index, and the key characteristic parameter evaluation index is used to evaluate the operating fault degree of the blade of the specified wind turbine at the next moment; The current vibration characteristic judgment module is used to compare the acquired key characteristic parameter evaluation index with the vibration data reference model to judge whether the current vibration characteristic of the specified wind turbine blade is abnormal.

Images