CN114689320A - Wind turbine generator bearing fault detection method and device, controller and storage medium - Google Patents

Abstract

The present application discloses a method, device, controller and storage medium for detecting a bearing fault of a wind turbine. The method for detecting a bearing fault of a wind turbine includes acquiring operating parameters of the wind turbine, the operating parameters including the acceleration of the nacelle and the rotational speed of the wind turbine; when the rotational speed is in a stable state, high-pass filtering is performed on the acceleration of the nacelle, Obtaining the target acceleration within a preset frequency range; extracting the frequency domain feature of the target acceleration; and detecting whether the bearing of the wind turbine generator fails according to the frequency domain feature and the rotational speed. By adopting the method, device, controller and storage medium for fault detection of a wind turbine bearing provided by the present application, the power generation performance and service life of the wind turbine can be improved.

Description

Wind turbine bearing fault detection method, device, controller and storage medium

technical field

The present application relates to the technical field of wind power generation, and in particular, to a method, device, controller and storage medium for fault detection of a wind turbine bearing.

Background technique

Bearing is an important component of wind turbine, once it fails, it will affect the power generation performance and life of the wind turbine. Therefore, the fault detection of the bearing of the wind turbine has also become particularly important.

At this stage, the temperature detection method is usually used for bearing fault detection. Specifically, a temperature sensor can be used to collect the temperature of the bearing, and when the temperature reaches a set temperature threshold, it is prompted that the bearing temperature is too high and a fault occurs. However, when the bearing is seriously worn, the temperature of the bearing will increase significantly. In this way, the failure of the bearing can only be detected after the bearing has been severely worn, which may cause the wind turbine to operate in a sub-healthy state for a long time, which will affect the power generation performance and life of the wind turbine.

SUMMARY OF THE INVENTION

The purpose of the embodiments of the present application is to provide a fault detection method, device, controller and storage medium for a bearing of a wind turbine, so as to solve the problem that in the prior art, the fault of the bearing can only be detected after the bearing has been severely worn, resulting in a long-term failure of the wind turbine. Operating in a sub-healthy state, which in turn affects the power generation performance and life of the wind turbine.

The technical solution of this application is as follows:

In a first aspect, a method for detecting a bearing fault of a wind turbine is provided, including:

acquiring operating parameters of the wind turbine, the operating parameters including the acceleration of the nacelle and the rotational speed of the wind turbine;

When the rotational speed is in a stable state, high-pass filtering is performed on the cabin acceleration to obtain a target acceleration within a preset frequency range;

extracting the frequency domain feature of the target acceleration;

According to the frequency domain feature and the rotational speed, it is detected whether the bearing of the wind turbine is faulty.

In a second aspect, a wind turbine bearing fault detection device is provided, including:

an acquisition module, configured to acquire operating parameters of the wind turbine, where the operation parameters include the acceleration of the nacelle and the rotational speed of the wind turbine;

a filtering module, configured to perform high-pass filtering on the acceleration of the cabin when the rotational speed is in a stable state to obtain a target acceleration within a preset frequency range;

an extraction module for extracting the frequency domain feature of the target acceleration;

A detection module, configured to detect whether the bearing of the wind turbine generator fails according to the frequency domain feature and the rotational speed.

In a third aspect, a controller is provided, the controller may include:

a processor; and a memory storing computer program instructions;

The processor reads and executes the computer program instructions, and the processor reads and executes the computer program instructions to implement the method for detecting a bearing fault of a wind turbine as shown in any one of the embodiments of the first aspect .

In a fourth aspect, a readable storage medium is provided, where computer program instructions are stored on the readable storage medium, and when the computer program instructions are executed by a processor, implement the wind turbine as shown in any one of the embodiments of the first aspect Bearing fault detection method.

The technical solutions provided by the embodiments of the present application bring at least the following beneficial effects:

In the embodiment of the present application, by acquiring the operating parameters of the wind turbine including the acceleration of the nacelle and the rotational speed of the wind turbine, when the rotational speed is in a stable state, high-pass filtering is performed on the acceleration of the engine room to obtain a target acceleration within a preset frequency range, and the target acceleration is extracted. According to the frequency domain characteristics of the target acceleration and the rotational speed, it is detected whether the bearing of the wind turbine is faulty. In this way, since the acceleration of the nacelle will change significantly when the bearing is slightly worn or there is foreign matter, therefore, based on the acceleration of the nacelle, when the bearing is slightly worn or there is foreign matter, the bearing of the wind turbine can be detected. Maintenance at the early stage of failure can prevent the wind turbine from running in a sub-healthy state for a long time, and improve the power generation performance and life of the wind turbine.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not limiting of the present application.

Description of drawings

The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, serve to explain the principles of the present application, and do not constitute an improper limitation of the present application.

1 is a frequency spectrum diagram of a cabin acceleration provided by an embodiment of the present application;

2 is a frequency spectrum diagram of a cabin acceleration provided by an embodiment of the present application;

3 is a frequency spectrum diagram of a cabin acceleration provided by an embodiment of the present application;

4 is a frequency spectrum diagram of a cabin acceleration provided by an embodiment of the present application;

5 is a schematic flowchart of a method for detecting a bearing fault of a wind turbine according to an embodiment of the present application;

6 is a schematic flowchart of a method for detecting a bearing fault of a wind turbine provided by an embodiment of the present application;

7 is a schematic flowchart of a method for detecting a bearing fault of a wind turbine provided by an embodiment of the present application;

8 is a schematic flowchart of a method for detecting a bearing fault of a wind turbine according to an embodiment of the present application;

9 is a schematic structural diagram of a wind turbine bearing fault detection device provided by an embodiment of the present application;

FIG. 10 is a schematic structural diagram of a controller provided by an embodiment of the present application.

Detailed ways

In order to make those skilled in the art better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings.

It should be noted that the terms "first", "second", etc. in the description and claims of the present application and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that data so used may be interchanged under appropriate circumstances so that the embodiments of the application described herein can be practiced in sequences other than those illustrated or described herein. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as recited in the appended claims.

Based on the background technology, it can be known from the prior art that the temperature detection method is used for bearing fault detection. Since the bearing failure can only be detected after the bearing has been seriously worn, the wind turbine will run in a sub-healthy state for a long time, which will affect the The power generation performance and life of wind turbines.

In addition, under normal operation of the wind turbine, there is no impact between the inner ring of the bearing of the wind turbine and the rolling elements. When the bearing of the wind turbine is faulty, such as uneven friction of the bearing due to cracks or foreign objects in the bearing, it will cause periodic impact between the inner ring of the bearing and the rolling elements of the wind turbine. In the frequency spectrum of the nacelle acceleration It is reflected in the characteristic frequency and frequency multiplication.

Specifically, as shown in FIG. 1 , in the normal operation state of the wind turbine, the frequency spectrum of the acceleration of the nacelle usually only contains low-frequency components generated by the rotational frequency of the impeller. As shown in Figure 2, Figure 3, and Figure 4, when the bearing of the wind turbine has failure characteristics such as wear, foreign matter, cracks, etc. that cause the bearing to fail, there will be collision between the inner ring of the bearing and the rolling elements, resulting in the frequency spectrum of the acceleration of the engine room. The eigenfrequencies and octaves appear in the graph.

Based on the above findings, the embodiments of the present application provide a method, device, controller, and storage medium for detecting a bearing fault of a wind turbine. In the case of high-pass filtering of the cabin acceleration, the target acceleration within the preset frequency range is obtained, the frequency domain characteristics of the target acceleration are extracted, and then according to the frequency domain characteristics and rotational speed of the target acceleration, it is detected whether the bearing of the wind turbine is faulty. In this way, since the acceleration of the nacelle will change significantly when the bearing is slightly worn or there is foreign matter, therefore, based on the acceleration of the nacelle, when the bearing is slightly worn or there is foreign matter, the bearing of the wind turbine can be detected. Maintenance at the early stage of failure can prevent the wind turbine from running in a sub-healthy state for a long time, and improve the power generation performance and life of the wind turbine.

The following first describes a method for detecting a bearing fault of a wind turbine provided by an embodiment of the present application.

FIG. 5 shows a schematic flowchart of a method for detecting a bearing fault of a wind turbine provided by an embodiment of the present application. The execution body of the method may be a controller of a wind turbine, or an industrial computer, a cloud server, or other equipment of a wind farm. As shown in FIG. 5 , the method for detecting a bearing fault of a wind turbine may include the following steps:

S510, obtain the operating parameters of the wind turbine.

The operating parameters may include the acceleration of the nacelle and the rotational speed of the wind turbine.

During the operation of the wind turbine, the vibration sensor installed in the wind turbine cabin to detect the vibration of the whole machine, or the vibration sensor of the Content Management System (CMS) installed on the bearing of the wind turbine, collects The nacelle acceleration of the wind turbine; the rotational speed of the wind turbine is collected by the rotational speed sensor of the wind turbine. Then, the operating parameters of the wind turbine can be obtained, for example, the operation parameters of the wind turbine can be obtained periodically, and the operation parameters can include the nacelle acceleration and rotational speed of the wind turbine collected above.

S520 , when the rotational speed is in a stable state, perform high-pass filtering on the acceleration of the cabin to obtain a target acceleration within a preset frequency range.

The preset frequency range may be a preset frequency range allowed to pass through the high-pass filter, and the frequency range may be set to a higher frequency range, so that the high-pass filter process can filter out low-frequency signals generated by components such as impellers.

The target acceleration may be a cabin acceleration within a preset frequency range among the cabin accelerations.

After obtaining the operating parameters of the wind turbine including the acceleration of the nacelle and the rotational speed of the wind turbine, it can be judged whether the rotational speed of the wind turbine is in a stable state. . How to determine whether the rotational speed of the wind turbine is in a stable state will be described in detail below, and will not be repeated here.

When the rotational speed of the wind turbine is in a stable state, high-pass filtering is performed on the acceleration of the engine room to filter out the acceleration of the engine room that does not belong to the preset frequency range. By processing such as weakening, the target acceleration in the cabin acceleration belonging to the preset frequency range is obtained. For example, Butterworth high-pass digital filter, Chebyshev filter, Bessel filter, etc. can be used for high-pass filtering. In this way, only the target cabin acceleration within the preset frequency range is retained, which can eliminate low-frequency noise in the cabin acceleration and reduce the impact of low-frequency signals on bearing fault detection.

S530, extract the frequency domain feature of the target acceleration.

Among them, the frequency domain feature is a coordinate system used to describe the characteristics of the signal in terms of frequency. For the cabin acceleration, the frequency domain feature can usually include the frequency and amplitude of the cabin acceleration.

After obtaining the target acceleration within the preset frequency range, the frequency domain feature of the target acceleration can be extracted. For example, a fast Fourier transform (fast Fourier transform, FFT) can be performed on the target acceleration to extract the frequency domain features of the target acceleration.

S540, according to the frequency domain feature and the rotational speed, detect whether the bearing of the wind turbine is faulty.

After the frequency domain feature of the target acceleration is extracted, it can be detected whether the bearing of the wind turbine is faulty according to the frequency domain feature of the nacelle acceleration and the rotational speed of the front-speed wind turbine. In this way, by using the frequency domain characteristics of the acceleration of the engine room, there will be obvious changes when the bearing is slightly damaged or there is foreign matter, and the fault condition of the bearing can be identified at an early stage, so as to perform maintenance for the fault condition at an early stage. For example, by improving the grease and operation strategy, after improving the grease and operation strategy, you can continue to observe the health of the bearing, conduct regular grease testing on the bearing, prepare bearing spare parts in advance, formulate a replacement plan, reduce unplanned downtime, avoid A condition of prolonged unplanned downtime caused by a stuck bearing.

It can be understood that, in the method for detecting a bearing fault of a wind turbine provided by the embodiment of the present application, after detecting that the bearing of the wind turbine is faulty, an early warning signal can also be output, so that the staff can receive the warning signal, wherein the warning The signal may include at least one of bearing fault indication information, maintenance mode information. In this way, it is not only possible to detect whether the bearing of the wind turbine is faulty at an early stage, but also to issue an early warning signal when it is detected that the bearing of the wind turbine is faulty, so that the staff can receive the early warning signal, and based on the early warning signal The bearing of the unit is maintained, so that the reliability and availability of the wind turbine can be improved.

In the embodiment of the present application, by acquiring the operating parameters of the wind turbine including the acceleration of the nacelle and the rotational speed of the wind turbine, when the rotational speed is in a stable state, high-pass filtering is performed on the acceleration of the engine room to obtain a target acceleration within a preset frequency range, and the target acceleration is extracted. According to the frequency domain characteristics of the target acceleration and the rotational speed, it is detected whether the bearing of the wind turbine is faulty. In this way, since the acceleration of the nacelle will change significantly when the bearing is slightly worn or there is foreign matter, therefore, based on the acceleration of the nacelle, when the bearing is slightly worn or there is foreign matter, the bearing of the wind turbine can be detected. Maintenance at the early stage of failure can prevent the wind turbine from running in a sub-healthy state for a long time, and improve the power generation performance and life of the wind turbine.

Moreover, in the embodiment of the present application, the vibration sensor of the wind turbine installed inside the nacelle for detecting the vibration of the whole machine, or the vibration sensor of the CMS installed on the bearing of the wind turbine, is used to collect the acceleration of the nacelle of the wind turbine to be based on The acceleration of the nacelle realizes the fault detection of the bearing of the wind turbine. In this way, on the one hand, there is no need to install other equipment separately, and the acquisition of the nacelle acceleration can be realized by using the existing equipment, which can make the wind turbine bearing fault detection method provided by the embodiment of the present application low in cost; on the other hand, since the existing equipment is installed inside the nacelle The accuracy of the vibration sensor of the CMS, or the vibration sensor of the CMS is usually high, and the accuracy of the collected nacelle acceleration is also high, so that the accuracy of the wind turbine bearing fault detection method provided by the embodiment of the present application can be improved.

In some embodiments, the frequency domain feature may include an amplitude value and a frequency corresponding to the amplitude value. In this case, the bearing of the wind turbine may be detected according to the amplitude value and frequency in the frequency domain feature, and the characteristic frequency and frequency multiplier determined based on the rotational speed. Whether a fault occurs, correspondingly, the specific implementation manner of the above step S540 may be as follows:

Obtain the M first target amplitudes with the largest value among the amplitudes of the frequency domain features, where M is a positive integer;

For M first target amplitudes, determine the first target frequency corresponding to each first target amplitude, and obtain M first target frequencies;

Calculate the characteristic frequency and multiplier n of the bearing according to the rotational speed, where n is a positive integer;

Based on the M first target frequencies, characteristic frequencies and multipliers, it is detected whether the bearing of the wind turbine is faulty.

In the case where the frequency-domain characteristics of the cabin acceleration include amplitude and frequency, the M amplitudes with the largest values among all the amplitudes of the frequency-domain characteristics can be determined first, that is, the M first target amplitudes, where M can be A positive integer, such as 2. For the aforementioned M first target amplitudes, the frequency corresponding to each first target amplitude, ie, the first target frequency, may be determined from all frequencies of the frequency domain feature, and M first target frequencies are obtained. Then, the characteristic frequency and frequency multiplication of the bearing can be calculated according to the rotational speed of the wind turbine, and then whether the bearing of the wind turbine is faulty can be detected according to the M first target frequencies and the aforementioned characteristic frequency and frequency multiplication.

As a specific example, the characteristic frequency X can be calculated based on formulas (1) and (2):

X=co _inne *freq _gs (1)

Among them, co _inne is the characteristic frequency coefficient of the inner ring of the bearing, and the characteristic frequency coefficient may be the coefficient of the inner ring of the bearing, the coefficient of the outer ring of the bearing, the coefficient of the rolling system, the coefficient of the cage, and the like. freq _gs is the rotational frequency, and the value of freq _gs is the average rotational speed/60 in the steady state of the rotational speed. n is the frequency multiplier, n=1, 2, 3,...k, the value of k is closely related to the characteristic frequency coefficient of the bearing, n*X is less than or equal to the sampling frequency of the engine room acceleration/2.

Taking M=2 as an example, the specific implementation method for determining the M first target frequencies may be: first, from all the amplitudes of the cabin acceleration, find the first target amplitude with the largest amplitude, denoted as amp1, and all Among the amplitudes, the first target amplitude with the largest amplitude except amp1 is denoted as amp2. The first target frequency corresponding to each amp1 and amp2 is determined, and denoted as freq1 and freq2. It should be noted that, in order to avoid interference to the extraction of freqa (a=1,2) caused by adjacent frequency signals, before freq2 is extracted, the amplitudes in a preset number of neighborhoods around freq1 can be set to 0. The preset number of typical The value can take 10.

It can be understood that the amplitudes in the non-frequency domain features of freq1 and freq2 are strictly arranged from large to small to the frequencies corresponding to the first two amplitudes. Specifically, due to the need to consider the interference of adjacent frequencies. For example, amp1=0.8g at freq1=0.51Hz is the largest amplitude in the frequency domain feature, if the amplitude 0.75g at 0.52Hz is the second largest amplitude after amp1, but 0.52Hz and freq1 constitute a neighbor Domain relationship, so the frequency at 0.52Hz is not used as freq2. Based on the above considerations, a processing method in which the frequency domain amplitude in the neighborhood is set to 0 is made when extracting the first target amplitude.

In this way, when the bearing of the wind turbine has failure characteristics such as wear, foreign matter, cracks, etc., which lead to the failure of the bearing, the characteristic frequency and frequency doubling will appear in the frequency domain characteristics of the nacelle acceleration. Therefore, according to the frequency corresponding to the amplitude with the largest value, and the characteristic frequency and frequency multiplier determined based on the rotational speed of the wind turbine, the fault condition of the bearing of the wind turbine can be detected, which can further improve the accuracy of the detection result.

In some embodiments, in the case where the M first target amplitudes are greater than or equal to a preset amplitude threshold, the first target frequency corresponding to each first target amplitude may be determined to obtain M first target amplitudes. target frequency.

After the M first target amplitudes are determined, the M first target amplitudes may be compared with a preset amplitude threshold to determine whether there is a value greater than or equal to the preset amplitude threshold in the M first target amplitudes The first target amplitude value of , for example, the preset amplitude threshold value may be 0.02, and the specific value of the preset amplitude threshold value may be set according to actual requirements. If there is a first target amplitude greater than or equal to the preset amplitude threshold among the M first target amplitudes, then determine the first target frequency corresponding to each first target amplitude, and obtain M first target amplitudes frequency, and perform the subsequent steps of determining the characteristic frequency and frequency multiplication of the bearing according to the rotational speed, and detecting whether the bearing of the wind turbine is faulty based on the M first target frequencies, characteristic frequencies and frequency multiplication. In the case where there is no first target amplitude greater than or equal to the preset amplitude threshold among the M first target amplitudes, that is, the situation where any one of the M first target amplitudes is smaller than the preset amplitude threshold If the following conditions are used, the steps of whether the bearing of the subsequent wind turbine is faulty are not performed.

In this way, in the case where the M first target amplitudes are all smaller than the preset amplitude threshold, the probability of the bearing failure of the wind turbine is very small, therefore, there may be only M first target amplitudes greater than or equal to The first target amplitude of the preset amplitude threshold is used to detect whether the bearing of the wind turbine is faulty. In this way, the success rate and efficiency of the wind turbine bearing fault detection method can be improved, and the unnecessary calculation amount and resource consumption can be reduced to a certain extent.

In some embodiments, it may be determined whether the wind turbine is faulty in combination with the frequencies corresponding to the maximum magnitudes of the acceleration of the nacelle in the two directions. Correspondingly, its specific implementation can be as follows:

The cabin acceleration may include a spectrogram of a first cabin acceleration in a first direction, and a spectrogram of a second cabin acceleration in a second direction.

The first direction may be perpendicular to the second direction, and the first direction and the second direction may be two mutually perpendicular directions in the coordinate system, for example, the first direction may be the x direction, and the second direction may be the y direction.

Spectrograms can be used to represent the frequency versus magnitude of the cabin acceleration through the spectrum.

At this time, the above-mentioned specific implementation method for detecting whether the bearing of the wind turbine is faulty based on the M first target frequencies, characteristic frequencies and frequency multipliers may be as follows:

Calculate the first n-octave based on the eigenfrequency and the octave,

According to the first n-octave frequency, determine the first target n-octave frequency corresponding to the maximum amplitude in the first frequency interval in the spectrogram of the first cabin acceleration, and the second frequency in the spectrogram of the second cabin acceleration The second target n multiplier corresponding to the largest amplitude in the interval;,

Among the M first target frequencies, if there is a first target frequency that is the same as the first target n-multiplied frequency or the second target n-multiplied frequency, it is determined that the bearing of the wind turbine is faulty.

Wherein, the first frequency interval is a frequency interval in which the frequency deviation from the first n-multiplier nX frequency is within the first deviation range, that is, the frequency interval in which the frequency deviation from nX is within the first deviation range. The second frequency interval is the frequency interval in which the frequency deviation from the first n-multiplier is within the second deviation range, that is, the frequency interval in which the frequency deviation from nX is in the second deviation range. The first deviation range may be the same as or different from the second deviation range.

The first n-multiplier is an n-multiplier calculated based on the characteristic frequency X and the multiplier n calculated above.

The nacelle acceleration may include a first nacelle acceleration in a first direction and a second nacelle acceleration in a second direction. At this time, the bearing n multiplication frequency nX, that is, the first n multiplication frequency, can be calculated based on the above-mentioned characteristic frequency X and frequency multiplication n. Determine the maximum amplitude in the first frequency interval in the spectrogram of the first cabin acceleration, and then determine the frequency corresponding to the maximum amplitude, that is, the first target n-multiplier, which can also be called the n-multiplier in the first direction. . The aforementioned formulas for calculating the n-multiplier of the first target may be as formulas (3) and (4).

nX _amp = max(amp[nX-ε,nX+ε]) (3)

nX-ε<freq _max <nX+ε (4)

Wherein, nX _amp represents the maximum amplitude in the preset frequency range around nX frequency in the spectrogram of the first cabin acceleration; ε represents the aforementioned preset frequency range; freq _max represents the n-multiplier of the first target.

Similarly, it is also possible to determine the maximum amplitude in the second frequency interval in the spectrogram of the second cabin acceleration, and then determine the frequency corresponding to the maximum amplitude, that is, the second target n-multiple frequency, which can also be called the second direction n times of frequency. The method for determining the n-multiplier of the second target is similar to the method for determining the n-multiplier of the first target, and details are not repeated here.

After the first target n-multiplier and the second target n-multiplier are determined, it can be determined whether there is a first target frequency that is the same as the first target n-multiplier or the second target n-multiplier in the above-mentioned M first target frequencies , that is, it can be determined whether there is an n-fold frequency of the first direction or the second direction in the first target frequency. Among the M first target frequencies, if there is a first target frequency that is the same as the first target n-multiplied frequency or the second target n-multiplied frequency, it is determined that the bearing of the wind turbine is faulty. That is, if there is at least one of the first target n-multiply frequency or the second target n-multiplier frequency among the M first target frequencies, it is considered that the bearing of the wind turbine is faulty.

In this way, based on the first n multiplier calculated by the characteristic frequency and the multiplier, the first target n multiplier and the second target n multiplier are determined, so that the determined first target n multiplier and the second target n multiplier can be made The frequency is more accurate, and then based on the first target n multiplier, the second target n multiplier, and the M first target frequencies to determine whether the bearing of the wind turbine is faulty, thereby further improving the accuracy of the wind turbine bearing detection result.

In some embodiments, it is possible to detect whether the bearing of the wind turbine is faulty when there is no interference frequency in the third frequency interval and the fourth frequency interval. Correspondingly, among the above M first target frequencies, there are In the case that the first target frequency is the same as the first target frequency n times or the second target frequency is the same as the first target frequency, before it is determined that the bearing of the wind turbine is faulty, the following steps may also be performed:

Determine whether the first interference frequency exists in the third frequency interval and the fourth frequency interval, respectively.

Wherein, the third frequency interval is the frequency interval where the frequency deviation from the first target n-multiple frequency is within the third deviation range, and the fourth frequency interval is the frequency where the frequency deviation from the second target n-multiple frequency is within the fourth deviation range interval, the third deviation range and the fourth deviation range may be the same or different.

At this time, in the above-mentioned situation that among the M first target frequencies, there is a first target frequency that is the same as the first target n-multiplier or the second target n-multiplier, the specific implementation method for determining that the bearing of the wind turbine is faulty may be as follows:

In the third frequency interval and the fourth frequency interval, there is no first interference frequency, and among the M first target frequencies, there is a first target that is the same as the n-multiplier of the first target or the n-multiplier of the second target In the case of frequency, it is determined that the bearing of the wind turbine is faulty.

The third frequency interval whose deviation range from the first target n-multiplier is the third deviation range and the fourth frequency interval whose deviation range from the second target n-multiplier is the fourth deviation range can be respectively determined. Then, it may be determined whether there is an interference frequency in the third frequency interval and the fourth frequency interval, that is, the first interference frequency. In the case where there is no first interference frequency in both the third frequency interval and the fourth frequency interval, determine whether there is a first target frequency that is the same as the n-multiple frequency of the first target or the n-multiple frequency of the second target among the M first target frequencies. a target frequency. There is no first interference frequency in both the third frequency interval and the fourth frequency interval, and among the M first target frequencies, there is a first target frequency that is the same as the first target n-multiplier or the second target n-multiplier In case of failure, it is determined that the bearing of the wind turbine is faulty. In the case that the first interference frequency exists in the third frequency interval or the fourth frequency interval, the step of detecting whether the bearing of the wind turbine is faulty is not performed.

The specific implementation manner of determining whether there is a first interference frequency in the third frequency interval may be: firstly identifying whether there is a first interference frequency in the frequency interval to the left of the first target n-multiple frequency in the third frequency interval, wherein the first target n The frequency interval on the left side of the multiplier can be a frequency interval whose frequency value is less than the first target n-multiplier and the difference from the first target n-multiplier is less than or equal to the third deviation range, and the first interference frequency can be nX _amp /co , where co is a constant, such as 3. Then, the maximum amplitude in the frequency interval on the left side of the first target n-multiplier in the third frequency interval can be determined, and denoted as left _amp , if left _amp <nX _amp /co, it is considered that the third frequency interval in the third frequency interval The first interference frequency does not exist in the frequency interval on the left side of a target n-multiple frequency. Similarly, the specific implementation method of determining whether there is a first interference frequency in the frequency interval to the right of the n-multiplier of the first target in the third frequency interval, and determining the left and right sides of the n-multiple frequency of the second target in the fourth frequency interval The specific implementation method of whether there is a first interference frequency in the frequency interval is similar to the specific implementation method of determining whether there is a first interference frequency in the frequency interval to the left of the n-multiplier of the first target in the third frequency interval, and will not be repeated here. .

It should be noted that it is also possible to comprehensively judge whether there is interference on the left and right sides of the frequency multiplier according to the area under the curve of the area near the n-multiplier frequency or the corresponding amplitude of each frequency component in the nearby area. The method for determining whether the first interference frequency is within the frequency interval is similar, and details are not repeated here.

In this way, it is considered that if the first interference frequency exists in the third frequency interval or the fourth frequency interval, the accuracy of the detection result of the bearing fault of the wind turbine may be affected. Therefore, only in the third frequency interval and the fourth frequency interval, when there is no first interference frequency, and in the M first target frequencies, there are n times the first target frequency or the second target frequency. In the case of the first target frequency with the same n-fold frequency, it is determined that the bearing of the wind turbine is faulty. In this way, the accuracy of the detection result of the bearing fault of the wind turbine can be further improved.

In some embodiments, the frequency domain feature may include a spectrogram of a first cabin acceleration in a first direction and a spectrogram of a second cabin acceleration in a second direction, the first direction being perpendicular to the second direction. The specific implementation manner of the above step S540 may be as follows:

Calculate the characteristic frequency and multiplier n of the bearing according to the rotational speed, where n is a positive integer;

Based on the eigenfrequency and frequency octave, determine the third target n octave corresponding to the respective maximum amplitudes under the n octave frequencies in the spectrogram of the first cabin acceleration, and the n octave frequencies in the spectrogram of the second cabin acceleration The fourth target n multiplier corresponding to the respective maximum amplitude;

According to the n third target n multiplication frequency and the n fourth target n multiplication frequency, it is detected whether the bearing of the wind turbine is faulty.

The characteristic frequency and frequency multiplication of the bearing can be calculated first according to the rotational speed. After the characteristic frequency and frequency multiplication of the bearing are determined, based on the characteristic frequency and frequency multiplication, the third target n multiplication frequency corresponding to the respective maximum amplitudes under the n frequency multiplication frequency in the spectrogram of the first engine room acceleration can be determined to obtain n n-multiples of the third target, and the fourth target n-multiples corresponding to the respective maximum amplitudes under the n-octave frequencies in the spectrogram of the acceleration of the second engine room, to obtain n fourth target n-multiples. According to the n third target n frequency multiplication and the n fourth target n frequency multiplication, it is detected whether the bearing of the wind turbine is faulty. It can be understood that the third target n-octave corresponding to the respective maximum amplitudes under the n-octave frequencies in the spectrogram of the first cabin acceleration is determined, and the respective n-octave frequencies in the spectrogram of the second cabin acceleration are determined. The specific implementation of the fourth target n-multiplication frequency corresponding to the maximum amplitude is the first target n-multiplication frequency corresponding to the maximum amplitude value in the spectrogram of the first cabin acceleration determined in the above-mentioned embodiment, and the second cabin acceleration. The specific implementation manner of the second target n-multiplier corresponding to the maximum amplitude in the spectrogram is similar, and details are not repeated here.

It should be noted that what is determined in this embodiment is the frequency corresponding to the respective maximum amplitude under each frequency multiplier. If n is assumed to be 6, then the frequency corresponding to the maximum amplitude value under 1 frequency multiplication, 2 times the frequency is determined. The frequency corresponding to the maximum amplitude under the frequency, ... the frequency corresponding to the maximum amplitude under the 6th frequency.

In this way, according to the n third target n-multipliers and n fourth target n-multipliers corresponding to the maximum amplitudes of the first cabin acceleration and the second cabin acceleration under each multiplier, the frequencies under different multipliers are comprehensively considered. Therefore, the accuracy of the detection results of the wind turbine bearing can be further improved.

In some embodiments, according to the n third target n multiplication frequency and n fourth target n multiplication frequency, the specific implementation manner of detecting whether the bearing of the wind turbine is faulty may be as follows:

It is respectively determined whether there is a second interference frequency in the i-th fifth frequency interval and the i-th sixth frequency interval.

Among them, i is a positive integer less than or equal to n. And the i-th fifth frequency interval is the frequency interval in which the frequency deviation of the i-th third target n-multiplier is within the fifth deviation range, and the i-th sixth frequency interval is the i-th fourth target n-multiplier. The frequency range of the frequency deviation within the sixth deviation range;

In the case where the second interference frequency exists in the ith fifth frequency interval, the ith third target n-multiple frequency is removed from the n third target n-multiple frequencies, and the ith third target n-multiple frequency exists in the ith sixth frequency interval. In the case of two interference frequencies, the i-th fourth target n-multiple frequency is removed from the n fourth target n-multiple frequencies to obtain a first frequency set;

According to the first frequency set, it is detected whether the bearing of the wind turbine is faulty.

After obtaining n third target n-multiple frequencies and n fourth target n-multiple frequencies, it can be determined whether there is an interference frequency in the i-th fifth frequency interval and the i-th sixth frequency interval, that is, whether there is an interference frequency. The second interference frequency, the second interference frequency may be the same as the first interference frequency, or may be different from the first interference frequency. It should be noted that it is necessary to perform the aforementioned judgment on whether there is a second interference frequency for each of the third target n-multiplier and the fourth target n-multiplier, until it is determined whether each fifth frequency interval and sixth frequency interval exist. The second interference frequency. And the specific implementation method of determining whether there is a second interference frequency in the i-th fifth frequency interval and the i-th sixth frequency interval, respectively, is the same as the above-mentioned determining whether there is a first frequency interval in the third frequency interval and the fourth frequency interval. The implementation of the interference frequency is similar and will not be repeated here.

In the case that the second interference frequency exists in the ith fifth frequency interval, the ith third target n-multiple frequency may be removed from the n third target n-multiple frequencies. Similarly, in the case that the second interference frequency exists in the i-th sixth frequency interval, the i-th fourth target n-multiple frequency may be removed from the n fourth target n-multiple frequencies. A set is formed from all the third target n-multipliers and the fourth target n-multipliers that are not removed to obtain the first frequency set. Then, according to the first frequency set, it is detected whether the bearing of the wind turbine is faulty.

In this way, it is considered that if there is a second interference frequency in any of the fifth frequency interval or the sixth frequency interval, the accuracy of the detection result of the bearing fault of the wind turbine may be affected. Therefore, only the third target n-multiple frequency and the fourth target n-multiple frequency without the second interference frequency constitute the first frequency set, and whether the bearing of the wind turbine is faulty is determined according to the first frequency set. In this way, the accuracy of the detection result of the bearing fault of the wind turbine can be further improved.

In some embodiments, according to the first frequency set, the specific implementation manner of detecting whether the bearing of the wind turbine generator set is faulty may be as follows:

Obtain a preset threshold and the amplitude corresponding to each frequency in the first frequency set;

determining a second target amplitude whose amplitude is less than a preset threshold in the first frequency set;

removing the second target frequency corresponding to the second target amplitude in the first frequency set to obtain a second frequency set;

Perform de-duplication processing on all frequencies in the second frequency set to obtain a third frequency set;

According to the third frequency set, it is detected whether the bearing of the wind turbine is faulty.

After the first frequency set is obtained, the preset threshold value c can be obtained, where c is the allowable minimum value of the preset amplitude value, and the specific value of c can be set according to the actual situation, and the first frequency can also be obtained. The magnitude corresponding to each frequency in the set. Then, among all the amplitude values corresponding to each frequency of the first frequency set, an amplitude value smaller than c may be selected, that is, the second target amplitude value. All frequencies corresponding to the second target amplitude are removed from the first frequency set to obtain a second frequency set. Afterwards, the second frequency set can be de-duplicated to obtain a third frequency set, and based on the third frequency set, it is detected whether the bearing of the wind turbine is faulty.

In this way, based on removing the frequency corresponding to the amplitude smaller than the preset threshold, and performing the reprocessing of the third frequency set, to detect whether the bearing of the wind turbine is faulty, the unnecessary calculation amount can be reduced to a certain extent, thereby improving the Efficiency of a wind turbine bearing fault detection method.

In some embodiments, according to the third frequency set, the specific implementation manner of detecting whether the bearing of the wind turbine is faulty may be as follows:

Obtain a preset ratio set and any two frequencies in the third frequency set;

Calculate the ratio of any two frequencies;

If there is a target ratio belonging to the preset ratio set among all ratios, it is determined that the bearing of the wind turbine is faulty.

The preset ratio set may be a ratio set preset according to historical data or experience, which is denoted as ob _list .

When detecting whether the bearing of the wind turbine is faulty according to the first frequency set, a preset ratio set and any two frequencies in the third frequency set can be obtained, and the ratio of any two frequencies can be calculated to obtain the third frequency set. , the ratio of any two frequencies. Then, it can be determined whether there is a ratio belonging to the foregoing preset ratio set, that is, the target ratio, among all ratios calculated based on the frequencies in the third frequency set. If there is a target ratio belonging to the preset ratio set among all the ratios calculated based on the frequencies in the third frequency set, it can be considered that the bearing of the wind turbine is faulty.

It should be noted that, when calculating the ratio of any two frequencies in the third frequency set, it is necessary to use a frequency with a larger value than a frequency with a smaller value. And the elements in the preset ratio set are a series of elements with specific meaning greater than 1, and the elements in the preset ratio set may indicate that there are at least two frequency multiplications in the cabin acceleration signal of the bearing. And the method provided in this embodiment is executed when the number of elements in the third frequency set is greater than 1.

In this way, if there is a ratio belonging to the preset ratio set in the ratio of any two frequencies in the third frequency set, it means that there are at least two multipliers in the third frequency set, which means that the bearing of the wind turbine is faulty. In this way, the accuracy of the fault detection method for the bearing of the wind turbine can be further improved.

In some embodiments, the AC component of the high-pass filtered cabin acceleration may be determined as the target acceleration, and correspondingly, the specific implementation manner may be as follows:

Remove the DC component of the nacelle acceleration to obtain the AC component of the nacelle acceleration;

When the rotational speed is in a stable state, high-pass filtering is performed on the AC component of the cabin acceleration to obtain the target AC component within the preset frequency range in the AC component of the cabin acceleration;

The target AC component is determined as the target acceleration.

The cabin acceleration signal usually contains a DC component and an AC component. It is necessary to extract the AC component parasitic on the DC component, that is, it is necessary to remove the DC signal in the cabin acceleration. Specifically, the mean value of the cabin acceleration can be obtained first, and the process of removing the DC component is completed by subtracting the mean value from the cabin acceleration at each sampling time, as shown in formulas (5) and (6).

s(t)=x(t)-x ₀ (5)

Among them, s(t) is the AC component of the acceleration of the engine room; x(t) is the acceleration of the engine room; t is the sampling time; x ₀ is the mean value of the acceleration of the engine room, and T is the sampling period.

After removing the DC component of the cabin acceleration to obtain the AC component of the cabin acceleration, high-pass filtering can be performed on the AC component of the cabin acceleration to obtain the AC component of the AC component of the cabin acceleration that belongs to the preset frequency range, that is, the target AC component, And the target AC component can be determined as the target acceleration. The specific implementation principle of the high-pass filtering for the AC component of the cabin acceleration is similar to the specific implementation principle of the above-mentioned high-pass filtering for the cabin acceleration, and for the sake of brevity, it will not be repeated here.

In some embodiments, it may be determined whether the rotational speed is in a stable state according to the fluctuation coefficient of the rotational speed, and accordingly, the processing may be as follows:

Calculate the fluctuation coefficient of the speed;

When the fluctuation coefficient satisfies the preset fluctuation condition, it is determined that the rotational speed is in a stable state.

Among them, the fluctuation coefficient can be used to indicate the variation range of the rotational speed, such as standard deviation, coefficient of variation, extreme value, heat stroke, median difference, etc.

The fluctuation coefficient used to indicate the variation range of the rotational speed can be calculated to determine whether the fluctuation coefficient satisfies the preset fluctuation condition. When the fluctuation coefficient satisfies the preset fluctuation condition, it is determined that the rotational speed is in a stable state. On the contrary, when the fluctuation coefficient does not satisfy the preset condition, it is determined that the rotational speed is in an unstable state.

As a specific example, when the volatility coefficient is the standard deviation, the standard deviation can be calculated according to formula (7).

gs_std=max(gs)-min(gs) (7)

Among them, gs represents the rotational speed, and gs_std represents the standard deviation.

When the fluctuation coefficient is the standard deviation, the preset fluctuation condition may be that the standard deviation is less than the preset standard deviation threshold a, for example, a may be 0.1. When the standard deviation is less than a, the rotational speed can be considered to be in a stable state.

When the coefficient of variation is the coefficient of variation, the coefficient of variation can be calculated according to formula (8)

Among them, C _v represents the coefficient of variation, μ represents the average value of the rotational speed, and σ represents the standard deviation of the rotational speed.

In the case where the coefficient of variation is the coefficient of variation, the preset fluctuation condition may be that the coefficient of variation is smaller than the preset coefficient of variation threshold. When the coefficient of variation is less than the preset coefficient of variation threshold, the rotational speed can be considered to be in a stable state.

A method for detecting a bearing fault of a wind turbine provided by an embodiment of the present application will be described below with reference to FIG. 6 . As shown in FIG. 6 , the method for detecting a bearing fault of a wind turbine provided by the embodiment of the present application may perform the following steps:

S610, obtaining the operating parameters of the wind turbine.

Among them, the operating parameters include the acceleration of the nacelle and the rotational speed of the wind turbine.

S620, calculating the fluctuation coefficient of the rotational speed.

S630, whether the rotational speed is in a stable state.

Steps S640-S690 are performed when the rotational speed is in a stable state, otherwise, the process ends.

S640, calculate the characteristic frequency and frequency multiplication of the bearing according to the rotational speed.

S650, remove the DC component of the cabin acceleration.

S660, perform high-pass filtering on the AC component of the cabin acceleration to obtain the target acceleration.

S670, extract the frequency domain feature of the target acceleration through FFT.

S680, according to the frequency domain feature and the rotational speed, detect whether the bearing of the wind turbine is faulty.

S690, output the detection result.

The specific implementation principles and technical effects of the above steps are similar to the wind turbine bearing fault detection methods provided by the above method embodiments, and for the sake of brevity, details are not repeated here.

7 shows a method for detecting a bearing fault of a wind turbine provided by an embodiment of the present application. The method is a specific implementation process for detecting whether a bearing of a wind turbine is faulty based on M first target frequencies, characteristic frequencies and frequency multipliers. As shown in Figure 7, the method may include the following steps:

S710: Determine M first target amplitudes.

S720: Determine whether the M first target amplitudes have a first target amplitude that is greater than or equal to a preset amplitude threshold.

In the case that the M first target amplitudes are greater than or equal to the preset amplitude threshold, step S730 is executed. Otherwise, S770 is performed to end the process.

S730, for the M first target amplitudes, determine a first target frequency corresponding to each first target amplitude, and obtain M first target frequencies. And calculate the first n-octave based on the characteristic frequency and the multiplier, determine the first target n-octave corresponding to the maximum amplitude in the first frequency interval in the spectrogram of the first cabin acceleration, and the second cabin acceleration. The second target n-multiplication frequency corresponding to the largest amplitude in the second frequency interval in the spectrogram.

S740. Determine whether the first interference frequency exists in the third frequency interval and the fourth frequency interval, respectively.

In the case that the first interference frequency does not exist in the third frequency interval and the fourth frequency interval, step S750 is performed. Otherwise, S770 is performed to end the process.

S750: Determine whether there is a first target frequency that is the same as the first target n-multiplier or the second target n-multiplier among the M first target frequencies.

If there is a first target frequency that is the same as the first target n-multiplied frequency or the second target n-multiplied frequency among the M first target frequencies, step S760 is executed. Otherwise, S770 is performed to end the process.

S760, it is determined that the bearing of the wind turbine is faulty.

The specific implementation principles and technical effects of the above steps are similar to the wind turbine bearing fault detection methods provided by the above method embodiments, and for the sake of brevity, details are not repeated here.

8 shows a method for detecting a bearing fault of a wind turbine provided by an embodiment of the present application. The method is a specific implementation process of detecting whether a bearing of a wind turbine is faulty according to n third frequencies and n fourth frequencies. As shown in Figure 8, the method may include the following steps:

S810, based on the characteristic frequency and the frequency multiplier, determine the third target n-octave corresponding to the respective maximum amplitudes under the n-octave frequency in the spectrogram of the first cabin acceleration, and the n-octave in the spectrogram of the second cabin acceleration The fourth target n-multiplier corresponding to the respective maximum amplitude under the frequency multiplication.

S820, in the case where the second interference frequency exists in the ith fifth frequency interval, remove the ith third target n-multiple frequency from the n third target n-multiple frequencies, and store the ith third target n-multiple frequency in the ith sixth frequency interval In the case of the second interference frequency, the i-th fourth target n-multiple frequency is removed from the n fourth target n-multiple frequencies to obtain a first frequency set.

S830, remove the second target frequency corresponding to the second target amplitude in the first frequency set to obtain a second frequency set.

S840: Perform deduplication processing on all frequencies in the second frequency set to obtain a third frequency set.

S850, whether the number of elements in the third frequency set is greater than 1.

If the number of elements in the third frequency set is greater than 1, step S860 is performed. Otherwise, S880 is executed to end the process.

S860, whether there is a target ratio belonging to a preset ratio set among all ratios.

If there is a target ratio belonging to the preset ratio set among all ratios, step S870 is executed. Otherwise, S880 is executed to end the process.

S870, it is determined that the bearing of the wind turbine is faulty.

The specific implementation principles and technical effects of the above steps are similar to the wind turbine bearing fault detection methods provided by the above method embodiments, and for the sake of brevity, details are not repeated here.

Based on the same inventive concept, the present application also provides a fault detection device for a bearing of a wind turbine.

Fig. 9 is a schematic structural diagram of an apparatus for detecting a bearing fault of a wind turbine according to an exemplary embodiment. As shown in FIG. 9 , the wind turbine bearing fault detection device 900 may specifically include:

an acquisition module 910, configured to acquire operating parameters of the wind turbine, the operation parameters including the acceleration of the nacelle and the rotational speed of the wind turbine;

The filtering module 920 is configured to perform high-pass filtering on the cabin acceleration when the rotational speed is in a stable state, to obtain a target acceleration within a preset frequency range;

an extraction module 930, configured to extract the frequency domain feature of the target acceleration;

The detection module 940 is configured to detect whether the bearing of the wind turbine is faulty according to the frequency domain feature and the rotational speed.

In some embodiments, the frequency domain features may include amplitudes and frequencies corresponding to the amplitudes;

The detection module 940 may include:

a first acquisition unit, configured to acquire M first target amplitudes with the largest value among the amplitudes of the frequency-domain features, where M is a positive integer;

a first determining unit, configured to determine the first target frequencies corresponding to each of the first target amplitudes for the M first target amplitudes, and obtain the M first target frequencies;

The second determination unit is used to calculate the characteristic frequency and multiplier n of the bearing according to the rotational speed, where n is a positive integer;

The first detection unit is configured to detect whether the bearing of the wind turbine generator set is faulty based on the M first target frequencies, characteristic frequencies and frequency multipliers.

In some embodiments, the cabin acceleration includes a spectrogram of a first cabin acceleration in a first direction and a spectrogram of a second cabin acceleration in a second direction, the first direction being perpendicular to the second direction;

The first detection unit may include:

a calculation subunit, which can be used to calculate the first n-octave based on the characteristic frequency and the multiplier;

The first determination subunit can be used to determine, according to the first n-multiplier, the first target n-multiplier corresponding to the largest amplitude value in the first frequency interval in the spectrogram of the first cabin acceleration, and the second The second target n-multiple frequency corresponding to the maximum amplitude in the second frequency interval in the spectrogram of the acceleration;

The second determination subunit can be used to determine that the bearing of the wind turbine is faulty when there is a first target frequency that is the same as the first target n-multiple frequency or the second target n-multiple frequency among the M first target frequencies .

In some embodiments, the wind turbine bearing fault detection device 900 may further include:

The third determination unit can be used to determine whether there is a first interference frequency in the third frequency interval and the fourth frequency interval respectively, and the third frequency interval is the frequency deviation of n times of frequency from the first target within the first deviation range. frequency interval, the fourth frequency interval is the frequency interval in which the frequency deviation of n times the second target is within the second deviation range;

The second determination subunit can be specifically used for:

In the third frequency interval and the fourth frequency interval, there is no first interference frequency, and among the M first target frequencies, there is a first target that is the same as the n-multiplier of the first target or the n-multiplier of the second target In the case of frequency, it is determined that the bearing of the wind turbine is faulty.

In some embodiments, the frequency domain feature includes a spectrogram of a first cabin acceleration in a first direction and a spectrogram of a second cabin acceleration in a second direction, the first direction being perpendicular to the second direction;

The detection module 940 may include:

The second determination unit calculates the characteristic frequency and multiplier n of the bearing according to the rotational speed, where n is a positive integer;

The fourth determination unit is configured to determine, based on the characteristic frequency and the frequency multiplier, the third target n-octave corresponding to the respective maximum amplitudes under the n-octave frequency in the spectrogram of the first cabin acceleration, and the n-octave frequency of the second cabin acceleration. The fourth target n-multiplier corresponding to the respective maximum amplitudes under the n-octave frequency in the spectrogram;

The second detection unit is configured to detect whether the bearing of the wind turbine is faulty according to the n third target n-multipliers and the n fourth target n-multipliers.

In some embodiments, the second detection unit may include:

Determining subunits for respectively determining whether there is a second interference frequency in the i-th fifth frequency interval and the i-th sixth frequency interval, where i is a positive integer less than or equal to n;

The removal subunit is used to remove the ith third target n-multiple frequency from the n third frequencies when the second interference frequency exists in the ith fifth frequency interval, and in the ith sixth frequency interval In the case that the second interference frequency exists in the memory, the i-th fourth target n-multiple frequency is removed from the n fourth target n-multiple frequencies to obtain the first frequency set;

The detection subunit is used for detecting whether the bearing of the wind turbine generator fails according to the first frequency set.

In some embodiments, the detection subunit may include:

an amplitude acquisition subunit, used to acquire a preset threshold and an amplitude corresponding to each frequency in the first frequency set;

an amplitude determination subunit, configured to determine a second target amplitude whose amplitude is less than a preset threshold in the first frequency set;

a frequency removal subunit, configured to remove the second target frequency corresponding to the second target amplitude in the first frequency set to obtain a second frequency set;

a deduplication subunit, configured to perform deduplication processing on all frequencies in the second frequency set to obtain a third frequency set;

The fault detection sub-unit is used for detecting whether the bearing of the wind turbine is faulty according to the third frequency set.

In some embodiments, the fault detection subunit is specifically used for:

Obtain a preset ratio set and any two frequencies in the third frequency set;

Calculate the ratio of any two frequencies;

If there is a target ratio belonging to the preset ratio set among all ratios, it is determined that the bearing of the wind turbine is faulty.

In some embodiments, the wind turbine bearing fault detection device 900 may further include:

The straightening module is used to remove the DC component of the cabin acceleration to obtain the AC component of the cabin acceleration;

The filtering module 920 may include:

The filtering subunit performs high-pass filtering on the AC component of the cabin acceleration, and obtains the target AC component within the preset frequency range in the AC component of the cabin acceleration;

The fifth determination unit is used for determining the target AC component as the target acceleration.

In some embodiments, the wind turbine bearing fault detection device 900 may further include:

The calculation module is used to calculate the fluctuation coefficient of the rotational speed, and the fluctuation coefficient is used to indicate the variation range of the rotational speed;

The judgment module is used to determine that the rotational speed is in a stable state when the fluctuation coefficient satisfies the preset fluctuation condition.

The wind turbine bearing fault detection device provided in this embodiment can be used to execute the wind turbine bearing fault detection methods provided by the above method embodiments, and the implementation methods and technical effects thereof are similar, and are not repeated here.

Based on the same inventive concept, an embodiment of the present application further provides a controller. As shown in FIG. 10 , the controller may include a processor 1001 and a memory 1002 storing computer program instructions.

Specifically, the above-mentioned processor 1001 may include a central processing unit (CPU), or a specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured as one or more integrated circuits implementing the embodiments of the present invention.

Memory 1002 may include mass storage for data or instructions. By way of example and not limitation, memory 1002 may include a Hard Disk Drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive or two or more A combination of more than one of the above. Memory 1002 may include removable or non-removable (or fixed) media, where appropriate. Storage 1002 may be internal or external to the integrated gateway disaster recovery device, where appropriate. In certain embodiments, memory 1002 is non-volatile solid state memory. In particular embodiments, memory 502 includes read only memory (ROM). Where appropriate, the ROM may be a mask programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), electrically rewritable ROM (EAROM) or flash memory or A combination of two or more of the above.

The processor 1001 reads and executes the computer program instructions stored in the memory 1002 to implement any one of the wind turbine bearing fault detection methods in the foregoing embodiments.

In one example, the master controller may also include a communication interface 1003 and a bus 1010 . Among them, as shown in FIG. 10 , the processor 1001 , the memory 1002 , and the communication interface 1003 are connected through the bus 1010 and complete the mutual communication.

The communication interface 1003 is mainly used to implement communication between modules, devices, units, and/or devices in the embodiments of the present invention.

The bus 1010 includes hardware, software, or both, coupling the components of the master controller to each other. By way of example and not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), HyperTransport (HT) Interconnect, Industry Standard Architecture (ISA) Bus, Infiniband Interconnect, Low Pin Count (LPC) Bus, Memory Bus, Microchannel Architecture (MCA) Bus, Peripheral Component Interconnect (PCI) Bus, PCI-Express (PCI-X) Bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus or other suitable bus or a combination of two or more of the above. Bus 1010 may include one or more buses, where appropriate. Although embodiments of the present invention describe and illustrate a particular bus, the present invention contemplates any suitable bus or interconnect.

The controller may execute the method for detecting a bearing fault of a wind turbine in this embodiment of the present invention, thereby implementing the method and device for detecting a bearing of a wind turbine described in FIGS. 1 to 9 .

In addition, in combination with the wind turbine bearing fault detection method in the above embodiment, the embodiment of the present invention may provide a computer-readable storage medium for implementation. Computer program instructions are stored on the computer-readable storage medium; when the computer program instructions are executed by the processor, any one of the wind turbine bearing fault detection methods in the foregoing embodiments is implemented.

It is to be understood that the present invention is not limited to the specific arrangements and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above-described embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the sequence of steps after comprehending the spirit of the present invention.

The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an application specific integrated circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, elements of the invention are programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted over a transmission medium or communication link by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, and the like. The code segments may be downloaded via a computer network such as the Internet, an intranet, or the like.

It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps may be performed in the order mentioned in the embodiment, or may be different from the order in the embodiment, or several steps may be performed simultaneously.

The above are only specific implementations of the present invention, and those skilled in the art can clearly understand that, for the convenience and brevity of the description, for the specific working process of the above-described systems, modules and units, reference may be made to the foregoing method embodiments The corresponding process in , will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should all cover within the protection scope of the present invention.

Claims (13)

1. a wind turbine bearing fault detection method, is characterized in that, comprises: acquiring operating parameters of the wind turbine, the operating parameters including the acceleration of the nacelle and the rotational speed of the wind turbine; When the rotational speed is in a stable state, high-pass filtering is performed on the cabin acceleration to obtain a target acceleration within a preset frequency range; extracting the frequency domain feature of the target acceleration; According to the frequency domain feature and the rotational speed, it is detected whether the bearing of the wind turbine is faulty. 2. The method according to claim 1, wherein the frequency domain feature comprises an amplitude value and a frequency corresponding to the amplitude value; The detecting whether the bearing of the wind turbine is faulty according to the frequency domain feature and the rotational speed includes: Obtaining the M first target amplitudes with the largest value among the amplitudes of the frequency domain features, where M is a positive integer; For the M first target amplitudes, determine the first target frequency corresponding to each first target amplitude, and obtain M first target frequencies; Calculate the characteristic frequency and multiplier n of the bearing according to the rotational speed, and the n is a positive integer; Based on the M first target frequencies, the characteristic frequency and the frequency multiplier, it is detected whether the bearing of the wind turbine is faulty. 3. The method according to claim 2, wherein the cabin acceleration comprises a spectrogram of a first cabin acceleration in a first direction and a spectrogram of a second cabin acceleration in a second direction, the first direction being the same as the the second direction is vertical; The detecting whether the bearing of the wind turbine generator fails based on the M first target frequencies, the characteristic frequency and the frequency multiplier includes: Calculate the first n-octave based on the eigenfrequency and the multiplier, According to the first n-multiplier frequency, determine the first target n-multiplier frequency corresponding to the maximum amplitude in the first frequency interval in the spectrogram of the first cabin acceleration, and the frequency spectrum of the second cabin acceleration The second target n multiplier corresponding to the largest amplitude in the second frequency interval in the figure; If there is a first target frequency that is the same as the first target n-multiple frequency or the second target n-multiple frequency among the M first target frequencies, it is determined that the bearing of the wind turbine generator is faulty. 4. The method according to claim 3, characterized in that, in the M first target frequencies, there is a first target n-multiplied frequency or the second target n-multiplied frequency identical to In the case of a target frequency, before determining that the bearing of the wind turbine is faulty, the method further includes: Determine whether there is a first interference frequency in the third frequency interval and the fourth frequency interval respectively, and the third frequency interval is the frequency interval in which the frequency deviation of n times the first target frequency is within the third deviation range, so The fourth frequency interval is a frequency interval in which the frequency deviation of the n-multiplier from the second target is within the fourth deviation range; In the M first target frequencies, if there is a first target frequency that is the same as the first target n-multiplied frequency or the second target n-multiplied frequency, it is determined that the bearing of the wind turbine generator set occurs. failures, including: In the third frequency interval and the fourth frequency interval, the first interference frequency does not exist, and in the M first target frequencies, there is an n-fold frequency of the first target or the first target frequency. In the case that the two target n times the same first target frequency, it is determined that the bearing of the wind turbine is faulty. 5. The method according to claim 1, wherein the frequency domain feature comprises a spectrogram of a first cabin acceleration in a first direction and a spectrogram of a second cabin acceleration in a second direction, the first direction perpendicular to the second direction; The detecting whether the bearing of the wind turbine is faulty according to the frequency domain feature and the rotational speed includes: Calculate the characteristic frequency and multiplier n of the bearing according to the rotational speed, and the n is a positive integer; Based on the characteristic frequency and the frequency multiplier, determine the third target n-octave corresponding to the respective maximum amplitudes under the n-octave frequency in the spectrogram of the first cabin acceleration, and the frequency spectrum of the second cabin acceleration In the figure, the fourth target n-multiplier corresponding to the respective maximum amplitudes under the n multipliers; According to the n third target n frequency multiplication and the n fourth target n frequency multiplication, it is detected whether the bearing of the wind turbine is faulty. 6 . The method according to claim 5 , wherein the detecting whether the bearing of the wind turbine is faulty according to n third target n-multipliers and n fourth target n-multipliers, comprising: 6 . Determine whether there is a second interference frequency in the i-th fifth frequency interval and the i-th sixth frequency interval, where i is a positive integer less than or equal to the n; In the case where the second interference frequency exists in the i-th fifth frequency interval, the i-th third target n-multiple frequency is removed from the n third target n-multiple frequencies, and in the In the case that the second interference frequency exists in the i-th sixth frequency interval, the i-th fourth target n-multiple frequency is removed from the n fourth target n-multiple frequencies to obtain a first frequency set; According to the first frequency set, it is detected whether the bearing of the wind turbine is faulty. 7 . The method according to claim 6 , wherein the detecting whether the bearing of the wind turbine generator set fails according to the first frequency set comprises: 8 . obtaining a preset threshold and the amplitude corresponding to each frequency in the first frequency set; determining a second target amplitude whose amplitude is less than the preset threshold in the first frequency set; removing the second target frequency corresponding to the second target amplitude in the first frequency set to obtain a second frequency set; Perform deduplication processing on all frequencies in the second frequency set to obtain a third frequency set; According to the third frequency set, it is detected whether the bearing of the wind turbine is faulty. 8. The method according to claim 7, wherein the detecting whether the bearing of the wind turbine generator set fails according to the third frequency set comprises: acquiring a preset ratio set and any two frequencies in the third frequency set; Calculate the ratio of any two frequencies; If there is a target ratio belonging to the preset ratio set among all the ratios, it is determined that the bearing of the wind turbine is faulty. 9 . The method according to claim 1 , wherein when the rotational speed is in a stable state, high-pass filtering is performed on the cabin acceleration to obtain a target within a preset frequency range. 10 . Before acceleration, also include: removing the DC component of the cabin acceleration to obtain the AC component of the cabin acceleration; When the rotational speed is in a stable state, high-pass filtering is performed on the cabin acceleration to obtain a target acceleration within a preset frequency range, including: When the rotational speed is in a stable state, high-pass filtering is performed on the AC component of the cabin acceleration to obtain a target AC component within the preset frequency range in the AC component of the cabin acceleration; The target AC component is determined as the target acceleration. 10 . The method according to claim 1 , wherein when the rotational speed is in a stable state, high-pass filtering is performed on the cabin acceleration to obtain a target within a preset frequency range. 11 . Before acceleration, also include: calculating a fluctuation coefficient of the rotational speed, where the fluctuation coefficient is used to indicate a variation range of the rotational speed; When the fluctuation coefficient satisfies a preset fluctuation condition, it is determined that the rotational speed is in the stable state. 11. A wind turbine bearing fault detection device, characterized in that, comprising: an acquisition module, configured to acquire operating parameters of the wind turbine, where the operation parameters include the acceleration of the nacelle and the rotational speed of the wind turbine; a filtering module, configured to perform high-pass filtering on the acceleration of the cabin when the rotational speed is in a stable state to obtain a target acceleration within a preset frequency range; an extraction module for extracting the frequency domain feature of the target acceleration; A detection module, configured to detect whether the bearing of the wind turbine generator fails according to the frequency domain feature and the rotational speed. 12. A controller, characterized in that the controller comprises: a processor, and a memory storing computer program instructions; The processor reads and executes the computer program instructions to implement the method for detecting a bearing fault of a wind turbine according to any one of claims 1-10. 13. A readable storage medium, wherein computer program instructions are stored on the readable storage medium, and when the computer program instructions are executed by a processor, the wind power plant according to any one of claims 1-10 is implemented Unit bearing fault detection method.

Images