Direct-driven wind turbine generator main bearing fault diagnosis method, electronic equipment and storage medium

Abstract

The invention provides a direct-driven wind turbine generator main bearing fault diagnosis method, which comprises the following steps: dynamically calculating a fundamental wave frequency range related to an impeller rotating speed and expanding an analysis frequency band, screening frequency components with significant amplitudes in a vibration signal, and verifying a real-time rotating speed in combination with a frequency multiplication relationship; a low-frequency modulation area and a high-frequency inherent area are dynamically divided based on the rotating speed to perform dual-channel filtering, fault modulation features are extracted by using an envelope demodulation technology, a fault feature frequency model is generated in combination with bearing design parameters, and finally early warning is triggered through dual conditions of a threshold value and a trend. Accurate positioning of early faults of the main bearing is achieved, the problems that a traditional method is low in sensitivity and high in false alarm rate under the variable rotating speed working condition are solved, and the operation and maintenance efficiency and reliability of a wind turbine generator are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbines, and in particular to a method for diagnosing main bearing faults of a direct-drive wind turbine set, electronic equipment, and a storage medium. Background Art

[0002] Currently, the wind power industry has seen numerous cases of turbine main shaft failures, damage, and even removal from service, causing significant losses to wind farm operations. Most main shaft failures are caused by main bearing failures.

[0003] Due to the harsh operating environment, high impact loads, and variable speed and load characteristics of wind turbines, bearings are very likely to be damaged during operation. If early faults are not handled, they will rapidly develop and deteriorate during operation.

[0004] The wind power CMS system can be used to monitor the vibration status of the main bearing. Based on the CMS vibration signal, the main bearing operating status can be evaluated by analyzing characteristic parameters such as amplitude, effective value, spectrum, and kurtosis. However, this type of analysis is not sensitive to early bearing failures. The industry usually uses envelope analysis to identify early bearing failures. However, since the wind power main bearing operates under variable load and speed conditions, its effective fault information will be modulated at different frequencies with different speeds, and the effect of envelope demodulation depends largely on the selected bandwidth. Once the selected bandwidth does not cover the modulation area or the selected bandwidth area is large, the demodulation effect will be poor, making it difficult to identify fault characteristic information. In addition, in traditional methods, the filter bandwidth is generally selected at high frequencies. For the main bearings of wind power direct-drive units, the effective fault information is generally at low frequencies. This also makes the traditional envelope demodulation method ineffective when processing the vibration signals of direct-drive main bearings.

[0005] The present invention analyzes the operating status of the main bearing based on the CMS system and combines the envelope demodulation technology to extract the fault modulation characteristics, combines the bearing design parameters to generate a fault characteristic frequency model, and finally triggers an early warning through the dual conditions of threshold and trend. Summary of the Invention

[0006] A first aspect of the present disclosure provides a method for diagnosing a fault in a main bearing of a direct-drive wind turbine generator system, comprising the following steps:

[0007] Calculating a fundamental frequency range of the direct-drive wind turbine generator set according to the impeller speed range and the number of magnetic pole pairs of the direct-drive wind turbine generator set, and selecting a signal of a corresponding frequency range in the generator vibration signal of the direct-drive wind turbine generator set as a first interval signal according to the fundamental frequency range;

[0008] Filtering a signal within a preset range in the first interval signal as a second interval signal, extracting a signal in the second interval signal that satisfies a frequency doubling relationship as a target fundamental frequency, and calculating an impeller speed of the direct-drive wind turbine generator set according to the target fundamental frequency;

[0009] Determining a first fault area of the direct-drive wind turbine generator set according to the impeller speed, and determining a second fault area of the direct-drive wind turbine generator set based on a preset frequency range, wherein the preset frequency range is set according to the model of the direct-drive wind turbine generator set;

[0010] Filtering a vibration signal of a main bearing of the direct-drive wind turbine generator system according to the first fault area and the second fault area to obtain a first filtered signal and a second filtered signal;

[0011] Envelope demodulation is performed on the first filtered signal and the second filtered signal to obtain a first envelope spectrum and a second envelope spectrum, and the fault type of the main bearing of the direct-drive wind turbine generator set is determined in combination with the bearing fault characteristic frequency of the direct-drive wind turbine generator set.

[0012] Combined with the first aspect, the fundamental frequency is obtained by the formula Calculate, where p is the number of magnetic pole pairs of the direct drive generator and s is the impeller speed.

[0013] In combination with the first aspect, screening the signal of the corresponding frequency range in the generator vibration signal of the direct-drive wind turbine generator set according to the fundamental frequency range as the first interval signal specifically includes:

[0014] Expanding the fundamental frequency range according to a preset expansion amount to form a target fundamental frequency range including the fundamental frequency range and the expanded frequency band;

[0015] According to the target fundamental frequency range, a signal in a corresponding frequency range in the generator vibration signal of the direct-drive wind turbine generator set is filtered as a first interval signal.

[0016] In combination with the first aspect, screening a signal within a preset range in the first interval signal as a second interval signal, and extracting a signal in the second interval signal that satisfies a double frequency relationship as a target fundamental frequency includes:

[0017] sorting the first interval signals according to frequency amplitude, and screening a preset number of candidate frequencies;

[0018] The signal whose frequency multiplication relationship among the candidate frequencies satisfies the frequency multiplication relationship is taken as the target fundamental frequency.

[0019] In combination with the first aspect, the first fault area is a low-frequency modulation area that is dynamically adjusted based on the number of tooth slots, and its filtering range changes dynamically with the rotational speed.

[0020] In combination with the first aspect, determining the second fault area of the direct-drive wind turbine generator system based on the preset frequency range includes:

[0021] The preset high-frequency natural frequency band is selected according to the unit power, the lower limit of which is negatively correlated with the unit structural stiffness, and the upper limit does not exceed 1 / 2 of the sampling frequency.

[0022] In combination with the first aspect, performing envelope demodulation on the first filtered signal and the second filtered signal to obtain a first envelope spectrum and a second envelope spectrum includes:

[0023] extracting the signal amplitude fluctuation characteristics of the first filtered signal and the second filtered signal through a time domain envelope demodulation algorithm;

[0024] The signal amplitude fluctuation characteristics are analyzed to generate an envelope spectrum including the fault characteristic frequency and its harmonic components.

[0025] In combination with the first aspect, determining the fault type of the main bearing of the direct-drive wind turbine generator set in combination with the bearing fault characteristic frequency of the direct-drive wind turbine generator set includes:

[0026] Calculate the theoretical fault characteristic frequency set at the current speed based on the bearing geometric parameters;

[0027] Locating the neighborhood range of the theoretical fault characteristic frequency in the envelope spectrum and calculating the energy accumulation value;

[0028] If the ratio of the energy value of a certain fault characteristic frequency to the reference value in at least one envelope spectrum exceeds a preset threshold, or the energy growth trend meets the preset gradient condition, the corresponding fault type is determined.

[0029] According to a second aspect of the present disclosure, an electronic device is provided, comprising:

[0030] one or more processors;

[0031] The storage unit is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors can implement the direct-drive wind turbine main bearing fault diagnosis method.

[0032] A third aspect of the present disclosure provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for diagnosing a main bearing fault of a direct-drive wind turbine generator system can be implemented.

[0033] Beneficial Effects: The present disclosure provides a method, electronic device, and storage medium for diagnosing main bearing faults in direct-drive wind turbines. This method dynamically calculates the fundamental frequency range related to the impeller speed and expands the analysis frequency band, screening frequency components with significant amplitudes in the vibration signal and verifying the real-time speed by combining the frequency doubling relationship. It also dynamically divides the low-frequency modulation region and the high-frequency inherent region based on the speed for dual-channel filtering. It uses envelope demodulation technology to extract fault modulation features, and combines bearing design parameters to generate a fault characteristic frequency model. Finally, it triggers an early warning using both threshold and trend conditions. This method achieves precise positioning of early-stage main bearing faults, addresses the low sensitivity and high false alarm rate of traditional methods under variable speed conditions, and significantly improves the efficiency and reliability of wind turbine operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Schematic diagram of a flow chart of a method for diagnosing a fault of a main bearing of a direct-drive wind turbine according to an embodiment of the present disclosure;

[0035] Figure 2 This is an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0036] Exemplary embodiments are described in detail herein, with examples illustrated in the accompanying drawings. When the following description refers to the drawings, identical numerals in different drawings represent identical or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present disclosure.

[0037] The terms used in the embodiments of the present disclosure are for the purpose of describing specific embodiments only and are not intended to limit the embodiments of the present disclosure. The singular forms "a," "the," and "the" used in the embodiments of the present disclosure and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0038] A wind turbine CMS (Condition Monitoring System) is a system specifically designed to monitor and diagnose the operating status of key wind turbine components. It uses sensors to collect data on wind turbine vibration, temperature, oil levels, and other indicators. It then uses signal processing and intelligent algorithms to analyze the turbine's health, enabling early warning of faults and preventive maintenance.

[0039] Vibration signals are one of the most important monitoring parameters in a wind turbine CMS (Condition Monitoring System). They are used to monitor the operating status and potential faults of key wind turbine components, such as main bearings, gearboxes, and generators. By analyzing vibration signals, mechanical faults such as bearing wear, gear breakage, misalignment, looseness, and imbalance can be detected in advance, thereby improving wind turbine reliability and reducing unplanned downtime.

[0040] Traditional vibration signal analysis methods (such as time-domain, frequency-domain, and time-frequency analysis) have limited ability to detect early-stage bearing faults. This is especially true when a fault is just beginning (such as minor pitting or microcracks), where the vibration signal's energy is low and often drowned out by other mechanical noise. Therefore, improving the sensitivity of early-stage bearing fault detection has become a key area of optimization for wind turbine CMS systems.

[0041] Envelope analysis extracts high-frequency resonance signals through bandpass filtering to avoid interference from low-frequency mechanical noise.

[0042] The instantaneous amplitude (i.e., envelope) of the signal is calculated using the Hilbert transform, converting the characteristic frequencies of high-frequency impacts into low-frequency features for easier identification. The envelope signal is analyzed using the FFT spectrum to identify the characteristic frequencies of bearing faults (BPFI, BPFO, BSF, FTF).

[0043] The effectiveness of envelope demodulation is highly dependent on the selected bandwidth. If the bandwidth is not selected properly, it may result in:

[0044] The modulation information is not effectively covered, and the key fault characteristic frequencies cannot be extracted, resulting in missed detection.

[0045] The bandwidth is too large, which introduces irrelevant signals and excessive background noise interference, thus masking the fault characteristics.

[0046] If the bandwidth is too small, it will lead to information loss and may lose key harmonic components, affecting feature extraction.

[0047] like Figure 1 FIG. 1 is a flow chart of a method for diagnosing a main bearing fault of a direct-drive wind turbine according to an embodiment of the present disclosure, comprising:

[0048] S101: Calculating a fundamental frequency range of the direct-drive wind turbine according to an impeller speed range and a magnetic pole pair number of the direct-drive wind turbine, and selecting a signal of a corresponding frequency range in a generator vibration signal of the direct-drive wind turbine as a first interval signal according to the fundamental frequency range;

[0049] S102: Filtering a signal within a preset range in the first interval signal as a second interval signal, extracting a signal in the second interval signal that satisfies a frequency doubling relationship as a target fundamental frequency, and calculating an impeller speed of the direct-drive wind turbine generator system according to the target fundamental frequency;

[0050] S103: determining a first fault area of the direct-drive wind turbine generator set according to the impeller speed, and determining a second fault area of the direct-drive wind turbine generator set based on a preset frequency range, wherein the preset frequency range is set according to the model of the direct-drive wind turbine generator set;

[0051] S104: filtering a vibration signal of a main bearing of the direct-drive wind turbine generator system according to the first fault area and the second fault area to obtain a first filtered signal and a second filtered signal;

[0052] S105: performing envelope demodulation on the first filtered signal and the second filtered signal to obtain a first envelope spectrum and a second envelope spectrum, and determining a fault type of a main bearing of the direct-drive wind turbine generator set in combination with a bearing fault characteristic frequency of the direct-drive wind turbine generator set.

[0053] Specifically, the calculation formula for the generator fundamental frequency is: Where p is the number of magnetic pole pairs of the direct-drive generator, and s is the impeller speed.

[0054] According to the impeller speed range designed for the unit (assuming it is (s1-s2) r / min), the fundamental frequency f1 range is: s1*p / 60 to s2*p / 60, and the fundamental frequency 2 times f2 range is: s1*p / 30 to s2*p / 30.

[0055] Furthermore, signals with a frequency range of s1*p / 60 to s2*p / 30 among the vibration signals obtained in the wind power CMS (Condition Monitoring System) are screened as first interval signals.

[0056] Optionally, the fundamental frequency range is expanded according to a preset expansion amount to form a target fundamental frequency range including the fundamental frequency range and the expanded frequency band.

[0057] Specifically, based on the frequency range of s1*p / 60 to s2*p / 30, a certain tolerance (preset extension amount) is left, for example, the frequency range can be set to s1*p / 60-4 to s2*p / 30+4 (target fundamental frequency range).

[0058] Then, according to the frequency range of s1*p / 60-4 to s2*p / 30+4 obtained after expansion, the signal corresponding to the frequency range of s1*p / 60-4 to s2*p / 30+4 in the generator vibration signal of the direct-drive wind turbine group is screened as the first interval signal.

[0059] Furthermore, signals within a preset range in the first interval signal are filtered as the second interval signal, and the preset range can be set according to actual working conditions.

[0060] Specifically, the first interval signals are sorted according to frequency amplitudes, and a preset number of candidate frequencies are screened; and signals whose frequency multiplication relationships among the candidate frequencies satisfy the frequency multiplication relationship are used as target fundamental frequencies.

[0061] For example, the frequencies of the first 10 amplitude values of the first interval signal obtained above are extracted and recorded as f 1-1 -f 1-10 , calculate two values with approximately 2-fold relationship among 10 frequencies, for example,

[0062] f 1-3 -0.5<2*f 1-1 <f 1-3 +0.5, then the fundamental frequency f1=f 1-1 The impeller speed s is calculated from the fundamental frequency, i.e. s = f1*60 / p.

[0063] The frequency multiplication relationship is not limited to 2 times and can be set according to actual conditions.

[0064] Furthermore, the first fault area of the direct-drive wind turbine generator set is determined according to the impeller speed. The first fault area is a low-frequency modulation area dynamically adjusted based on the number of tooth slots, that is, the first fault area filter lower limit f 1h =s*z / 60-20, the first fault area filter upper limit f 1z =s*z / 30+20, where z is the number of teeth in the direct-drive generator.

[0065] The second fault area of the direct-drive wind turbine generator set is determined based on a preset frequency range, and a preset high-frequency natural frequency band is selected according to the generator power. The lower limit is negatively correlated with the structural stiffness of the generator set, and the upper limit does not exceed 1 / 2 of the sampling frequency.

[0066] The second fault area is the component's inherent frequency modulation area, which is at high frequencies. Set the second area filter lower limit to f 2h , the upper limit of the filter is f 2z , such as 2MW model is set to 1500Hz, 6MW model is set to 800Hz; f 2z Regardless of the model, the setting is uniformly 3000Hz, but if f s When / 2<3000, then f2z =f s / 2. Where f s is the sampling frequency of the bearing vibration signal.

[0067] Furthermore, the vibration signal of the main bearing of the direct-drive wind turbine generator system is filtered according to the first fault area and the second fault area to obtain a first filtered signal and a second filtered signal.

[0068] Specifically, the main bearing vibration signal in the CMS is selected and filtered according to the upper and lower limits of the filter bandwidth in the two regions, respectively, to obtain the filtered signals data1 and data2.

[0069] Performing envelope demodulation on the first filtered signal and the second filtered signal to obtain a first envelope spectrum and a second envelope spectrum, and determining a fault type of a main bearing of the direct-drive wind turbine generator set in combination with a bearing fault characteristic frequency of the direct-drive wind turbine generator set, including:

[0070] extracting the signal amplitude fluctuation characteristics of the first filtered signal and the second filtered signal through a time domain envelope demodulation algorithm;

[0071] The signal amplitude fluctuation characteristics are analyzed to generate an envelope spectrum including the fault characteristic frequency and its harmonic components.

[0072] Specifically, in fault diagnosis, vibration signals often contain high-frequency carrier signals, while fault information is often hidden in their low-frequency modulation components. Therefore, directly analyzing the time-domain vibration signal is difficult to effectively extract fault characteristics. Instead, envelope demodulation is required to extract the signal's amplitude changes.

[0073] Bandpass filtering is performed on the first and second filtered signals to retain frequency bands that may contain fault information. A time-domain envelope demodulation algorithm, such as the Hilbert transform, is applied to extract the vibration signal's envelope, specifically the amplitude fluctuations. Smoothing filtering techniques are used to remove noise, improve signal quality, and enhance the accuracy of subsequent spectrum analysis.

[0074] The signal after envelope demodulation is still in the time domain. In order to further analyze the fault characteristics, it needs to be converted to the frequency domain, that is, to calculate the envelope spectrum.

[0075] Perform envelope demodulation on the signals data1 and data2 to obtain envelope spectra env1 and env2.

[0076] According to the bearing geometric parameters, the theoretical fault characteristic frequency set at the current speed is calculated and recorded as f in (inner race fault frequency), f out (outer race fault frequency), f ball (rolling element failure frequency), f tr (Cage failure frequency).

[0077] The calculated theoretical fault frequencies need to be matched in the envelope spectrum to verify whether there is abnormal energy accumulation at these frequencies.

[0078] The specific method is:

[0079] Find the neighborhood range of each fault characteristic frequency in the envelope spectrum to ensure that the signal is not missed due to measurement error.

[0080] The total energy value within the neighborhood, that is, the accumulated power spectrum density, is calculated to evaluate whether the frequency is abnormally prominent.

[0081] Envelope spectrum is a signal analysis technology that can extract modulation information. Compared with traditional spectrum analysis, it is more sensitive to early bearing failures. Therefore, this step is a key feature extraction process.

[0082] The fault type is determined by energy ratio or growth trend. The core of fault determination is energy ratio and growth trend analysis.

[0083] Energy ratio determination: Calculate the ratio between the energy value of the target fault frequency and the reference energy. If the ratio exceeds the preset threshold (e.g., R>3), it indicates that the frequency energy is abnormal and a fault may exist.

[0084] Energy growth trend determination: If the energy value of a certain fault characteristic frequency increases significantly over time and meets the preset growth gradient, it may indicate the occurrence of an early fault even if the current energy is low.

[0085] When any of the conditions is met, it can be determined that the main bearing may have a fault, and the fault type (such as inner ring damage, outer ring damage, etc.) can be further determined.

[0086] For example, when the energy value is greater than the set reference value*1.2, a first-level warning is issued to alert the operation and maintenance personnel to pay attention and check and confirm at an appropriate time;

[0087] When the energy value is greater than the set reference value*1.5, a second-level warning is issued to remind the operation and maintenance personnel to stop the machine for inspection as soon as possible; when the slope v>0.2, a second-level warning is issued to remind the operation and maintenance personnel to stop the machine for inspection as soon as possible.

[0088] The slope v is calculated as follows: when the energy value storage data exceeds 30 days, the slope v calculation program is started, and a straight line fitting is performed on the energy value of each fault frequency in the energy value to obtain their respective slopes. If any slope is greater than 0.2, an alarm is issued.

[0089] Regarding the method of obtaining the set reference value, the energy value calculated according to the above steps can be used as the set reference value at the initial operation of a new unit, or after the spindle is overhauled, or after the spindle is inspected and confirmed to be fault-free.

[0090] The electronic device 200 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 200 may include but is not limited to a processor 201 and a memory 202. Those skilled in the art will appreciate that Figure 2 This is merely an example of the electronic device 200 and does not constitute a limitation of the electronic device 200. The electronic device 200 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0091] The processor 201 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0092] The memory 202 can be an internal storage unit of the electronic device 200, such as a hard disk or memory of the electronic device 200. The memory 202 can also be an external storage device of the electronic device 200, such as a plug-in hard disk equipped on the electronic device 200, a smart memory card (SMC), a secure digital (SD) card, a flash card, etc. Furthermore, the memory 202 can also include both an internal storage unit of the electronic device 200 and an external storage device. The memory 202 is used to store the computer program 203 and other programs and data required by the electronic device. The memory 202 can also be used to temporarily store data that has been output or is about to be output.

[0093] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present disclosure, and should all be included in the scope of protection of the present disclosure.

Claims

1. A method for diagnosing faults of a main bearing of a direct-drive wind turbine generator system, characterized in that: The following steps are involved: Calculating a fundamental frequency range of the direct-drive wind turbine generator set according to the impeller speed range and the number of magnetic pole pairs of the direct-drive wind turbine generator set, and selecting a signal of a corresponding frequency range in the generator vibration signal of the direct-drive wind turbine generator set as a first interval signal according to the fundamental frequency range; Filtering a signal within a preset range in the first interval signal as a second interval signal, extracting a signal in the second interval signal that satisfies a frequency doubling relationship as a target fundamental frequency, and calculating an impeller speed of the direct-drive wind turbine generator set according to the target fundamental frequency; Determining a first fault area of the direct-drive wind turbine generator set according to the impeller speed, and determining a second fault area of the direct-drive wind turbine generator set based on a preset frequency range, wherein the preset frequency range is set according to the model of the direct-drive wind turbine generator set; Filtering a vibration signal of a main bearing of the direct-drive wind turbine generator system according to the first fault area and the second fault area to obtain a first filtered signal and a second filtered signal; Envelope demodulation is performed on the first filtered signal and the second filtered signal to obtain a first envelope spectrum and a second envelope spectrum, and the fault type of the main bearing of the direct-drive wind turbine generator set is determined in combination with the bearing fault characteristic frequency of the direct-drive wind turbine generator set.

2. The method according to claim 1, characterized in that The fundamental frequency is given by the formula Calculate, where p is the number of magnetic pole pairs of the direct-drive generator and s is the impeller speed.

3. The method according to claim 1, wherein The step of selecting a signal of a corresponding frequency range in the vibration signal of the generator of the direct-drive wind turbine generator set according to the fundamental frequency range as the first interval signal specifically includes: Expanding the fundamental frequency range according to a preset expansion amount to form a target fundamental frequency range including the fundamental frequency range and the expanded frequency band; According to the target fundamental frequency range, a signal in a corresponding frequency range in the generator vibration signal of the direct-drive wind turbine generator set is filtered as a first interval signal.

4. The method according to claim 1, wherein The step of screening a signal within a preset range in the first interval signal as a second interval signal, and extracting a signal in the second interval signal that satisfies a double frequency relationship as a target fundamental frequency includes: sorting the first interval signals according to frequency amplitude, and screening a preset number of candidate frequencies; The signal whose frequency multiplication relationship among the candidate frequencies satisfies the frequency multiplication relationship is taken as the target fundamental frequency.

5. The method according to claim 1, wherein The first fault area is a low-frequency modulation area that is dynamically adjusted based on the number of tooth slots, and its filtering range changes dynamically with the rotation speed.

6. The method according to claim 1, wherein Determining the second fault area of the direct-drive wind turbine generator system based on a preset frequency range includes: The preset high-frequency natural frequency band is selected according to the unit power, the lower limit of which is negatively correlated with the unit structural stiffness, and the upper limit does not exceed 1 / 2 of the sampling frequency.

7. The method according to claim 1, wherein The performing envelope demodulation on the first filtered signal and the second filtered signal to obtain a first envelope spectrum and a second envelope spectrum includes: extracting the signal amplitude fluctuation characteristics of the first filtered signal and the second filtered signal through a time domain envelope demodulation algorithm; The signal amplitude fluctuation characteristics are analyzed to generate an envelope spectrum including the fault characteristic frequency and its harmonic components.

8. The method according to claim 1, wherein Determining the fault type of the main bearing of the direct-drive wind turbine generator set in combination with the bearing fault characteristic frequency of the direct-drive wind turbine generator set includes: Calculate the theoretical fault characteristic frequency set at the current speed based on the bearing geometric parameters; Locating the neighborhood range of the theoretical fault characteristic frequency in the envelope spectrum and calculating the energy accumulation value; If the ratio of the energy value of a certain fault characteristic frequency to the reference value in at least one envelope spectrum exceeds a preset threshold, or the energy growth trend meets the preset gradient condition, the corresponding fault type is determined.

9. An electronic device, characterized in that: include: one or more processors; A storage unit is used to store one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the direct-drive wind turbine main bearing fault diagnosis method according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it can implement the direct-drive wind turbine main bearing fault diagnosis method according to any one of claims 1 to 8.

Images