Bearing fault diagnosis method and device, electronic equipment and storage medium

Abstract

This invention discloses a method, apparatus, electronic device, and storage medium for fault diagnosis of bearings. The fault diagnosis method includes: application to a wind turbine system, the wind turbine system including a drive chain, the drive chain including bearing components; the fault diagnosis method includes: acquiring vibration data of a target detection point on the drive chain; determining the vibration spectrum of the target detection point based on the vibration data; determining the sideband of a target frequency in the vibration spectrum; the target frequency being the fault frequency of the bearing component to be diagnosed; and performing fault diagnosis on the bearing component based on the sideband. This invention diagnoses the bearing components of a gearbox using vibration data from a generator and drive shaft. This method is easy to implement and has high accuracy. Even without a speed sensor or with a faulty speed sensor, timely fault diagnosis of the bearing components can be performed reliably and stably.

Description

Technical Field

[0001] This invention relates to the field of fault diagnosis, and more particularly to a method, apparatus, electronic device, and storage medium for diagnosing bearing faults. Background Technology

[0002] CMS (Conditional Monitoring System for Wind Turbines) is primarily used for monitoring and controlling operating equipment. It collects and stores high-frequency monitoring data from field equipment to facilitate process monitoring, fault detection, and diagnosis. Currently, fault diagnosis and analysis of bearing components typically requires installing speed sensors on the bearing components to obtain their rotational speed, and then diagnosing faults based on this speed. This method is not only costly but also susceptible to interference and has low accuracy. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to overcome the above-mentioned defects of the prior art and provide a bearing fault diagnosis method, device, electronic device, and storage medium.

[0004] The present invention solves the above-mentioned technical problems through the following technical solution:

[0005] Firstly, a method for diagnosing bearing faults is provided, applied to a wind turbine system, the wind turbine system including a drive chain, the drive chain including bearing components; the fault diagnosis method includes:

[0006] Acquire vibration data at target detection points on the transmission chain;

[0007] The vibration spectrum of the target detection point is determined based on the vibration data;

[0008] Determine the sideband of the target frequency in the vibration spectrum; the target frequency is the fault frequency of the bearing component to be diagnosed.

[0009] The bearing component is diagnosed based on the sideband.

[0010] Optionally, determining the sidebands of the target frequency in the vibration spectrum includes:

[0011] Determine the vibration frequency corresponding to the largest amplitude within the range of rotational speed variation in the vibration spectrum;

[0012] The actual rotational frequency of the fan is determined based on the average of at least two vibration frequencies with the smallest deviation;

[0013] The vibration spectrum is preprocessed based on the actual rotation frequency; the preprocessing includes dividing the horizontal axis of the vibration spectrum by the actual rotation frequency.

[0014] Determine the sidebands of the target frequency in the preprocessed vibration spectrum.

[0015] Optionally, determining the sidebands of the target frequency in the vibration spectrum includes:

[0016] The amplitude corresponding to the electrical frequency of the generator in the vibration spectrum is set to 0;

[0017] Determine the sidebands of the target frequency in the assigned vibration spectrum.

[0018] Optionally, determining the sidebands of the target frequency in the vibration spectrum includes:

[0019] Determine the center frequency corresponding to the maximum amplitude within the fault frequency range of the vibration spectrum;

[0020] Determine the sidebands of the target frequencies on both sides of the center frequency in the vibration spectrum;

[0021] The fault diagnosis of the bearing component based on the sideband includes:

[0022] The fault location range is determined based on the frequency of the sidebands;

[0023] Sum the maximum amplitude values ​​within the fault-finding range in the vibration spectrum;

[0024] The bearing components are then diagnosed based on the summation results.

[0025] Optionally, the fault diagnosis of the bearing component based on the summation result includes:

[0026] Based on the correspondence between weighted amplitude and fault type, the fault type corresponding to the weighted amplitude that matches the summation result is determined as the fault type of the bearing component.

[0027] Secondly, a bearing fault diagnosis device is provided, applied to a wind turbine system, the wind turbine system including a drive chain, the drive chain including bearing components; the fault diagnosis device includes:

[0028] The acquisition module is used to acquire vibration data of the target detection point on the transmission chain;

[0029] A spectrum determination module is used to determine the vibration spectrum of the target detection point based on the vibration data.

[0030] A frequency band determination module is used to determine the sideband of the target frequency in the vibration spectrum; the target frequency is the fault frequency of the bearing component to be diagnosed.

[0031] The fault diagnosis module is used to diagnose faults in the bearing components based on the sidebands.

[0032] Optionally, the frequency band determination module includes:

[0033] A vibration frequency determination unit is used to determine the vibration frequency corresponding to the largest amplitude value within the range of rotational speed change in the vibration spectrum.

[0034] The frequency determination unit is used to determine the actual frequency of the fan based on the average value of at least two vibration frequencies with the smallest deviation;

[0035] A preprocessing unit is used to preprocess the vibration spectrum according to the actual rotation frequency; the preprocessing includes dividing the horizontal axis of the vibration spectrum by the actual rotation frequency;

[0036] The frequency band determination unit is used to determine the sidebands of the target frequency in the preprocessed vibration spectrum.

[0037] Optionally, the frequency band determination module includes:

[0038] An amplitude unit is used to assign a value of 0 to the amplitude corresponding to the electrical frequency of the generator in the vibration spectrum;

[0039] The frequency band determination unit is used to determine the sidebands of the target frequency in the assigned vibration spectrum.

[0040] Optionally, the frequency band determination module includes:

[0041] A center frequency determination unit is used to determine the center frequency corresponding to the maximum amplitude value within the fault frequency range of the vibration spectrum.

[0042] Sideband determination unit, used to determine the sidebands of target frequencies on both sides of the center frequency in the vibration spectrum;

[0043] The fault diagnosis module includes:

[0044] A range determination unit is used to determine the fault search range based on the number of times the sideband is used.

[0045] The summation determination unit is used to sum the maximum amplitude values ​​within the fault search range in the vibration spectrum;

[0046] The fault diagnosis unit is used to diagnose faults in the bearing components based on the summation results.

[0047] Optionally, the fault diagnosis module is specifically used for:

[0048] Based on the correspondence between weighted amplitude and fault type, the fault type corresponding to the weighted amplitude that matches the summation result is determined as the fault type of the bearing component.

[0049] Thirdly, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and for running on the processor, wherein the processor executes the computer program to implement the bearing fault diagnosis method described in any of the preceding claims.

[0050] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the bearing fault diagnosis method described in any of the preceding claims.

[0051] Based on common knowledge in the field, the above-mentioned preferred conditions can be combined arbitrarily to obtain various preferred embodiments of the present invention.

[0052] The significant advantages of this invention are as follows: In this embodiment, fault diagnosis of the gearbox bearing components is performed using vibration data from the generator and drive shaft. This method is easy to implement and highly accurate. Even without a speed sensor or with a faulty speed sensor, timely fault diagnosis of the bearing components is possible, ensuring reliability and stability. Furthermore, this method of fault diagnosis of gearbox bearing components based on vibration data eliminates the need for a speed sensor, thus saving costs. Attached Figure Description

[0053] Figure 1 A schematic diagram of a fan drive train structure is provided for an exemplary embodiment of the present invention;

[0054] Figure 2 A flowchart of a bearing fault diagnosis method provided as an exemplary embodiment of the present invention;

[0055] Figure 3 for Figure 1 A specific flowchart of step 203;

[0056] Figure 4 for Figure 1 Another specific flowchart for step 203;

[0057] Figure 5 An effect diagram provided for using an exemplary embodiment of the present invention;

[0058] Figure 6 A schematic diagram of a bearing fault diagnosis device provided as an exemplary embodiment of the present invention;

[0059] Figure 7 This is a schematic diagram of the structure of an electronic device shown in an example embodiment of the present invention. Detailed Implementation

[0060] The present invention will be further illustrated by way of embodiments below, but the present invention is not limited to the scope of the embodiments described herein.

[0061] Figure 1 This is a schematic diagram of a wind turbine system provided as an exemplary embodiment of the present invention. The wind turbine system includes a wind turbine body 11 and a transmission chain. The transmission chain includes components such as an input shaft 12, a gearbox 13, and a generator 14. If these components fail, it will cause huge losses. Therefore, in order to better monitor the status of the wind turbine, vibration sensors are usually installed on each component of the transmission chain. For example, in order to monitor the drive end and non-drive end of the generator, vibration sensors are installed at these two measuring points; vibration sensors are also installed on the shaft system of the gearbox that changes speed to different speeds.

[0062] Experiments have shown that when a bearing component in the transmission chain experiences a significant fault, multiple harmonics of the bearing fault frequency will appear. The fault frequency ranges of different bearing components are not consistent. Taking a generator as an example, the bearing outer ring fault frequency equilateral band usually appears in the [0, 5000] frequency band. The more obvious the fault is in the low frequency band, the more severe the fault is. Therefore, this characteristic can be used to diagnose the bearing components.

[0063] Figure 2 A flowchart illustrating a bearing fault diagnosis method provided as an exemplary embodiment of the present invention is shown. This fault diagnosis method is applied to a wind turbine system. (See attached diagram.) Figure 2 The fault diagnosis method includes:

[0064] Step 201: Obtain vibration data of the target detection point on the transmission chain.

[0065] The transmission chain includes components such as an input shaft, gearbox, and generator. The target detection points include at least one of the following: detection points deployed on the generator, detection points deployed on the gearbox, and detection points deployed on the input shaft. Vibration sensors are deployed at each target detection point to collect vibration data. The number and deployment method of the target detection points can be determined according to actual conditions, and this embodiment of the invention does not impose any particular limitation on this. See also Figure 1 The gearbox's drive shaft includes a high-speed shaft directly connected to the generator and a low-speed shaft connected to the high-speed shaft. The detection points on the gearbox may include detection points located on the gearbox housing (see [link]). Figure 1 Points A to C in the diagram and / or detection points located on the drive shaft of the gearbox.

[0066] It should be noted that if vibration data from the generator and gearbox are combined to diagnose bearing components, that is, by combining vibration data from different measuring points of different components to find the fault characteristics of bearing components, the fault frequency of different components of the wind turbine can be accurately captured, thus improving the accuracy of fault diagnosis.

[0067] Vibration data can be used to observe the changes in the vibration amplitude of a fan over a period of time. Based on the vibration data, it is possible to observe whether the fan has periodic vibration. By converting the vibration data in the time domain into vibration data in the frequency domain, the vibration frequency of the fan can be analyzed, making it easier to understand the vibration characteristics of the fan and thus enabling accurate fault diagnosis of the fan bearings.

[0068] Step 202: Determine the vibration spectrum of the target detection point based on the vibration data.

[0069] Since the vibration data collected by the sensor is generally time-domain data, by performing a fast Fourier transform on the vibration data, the time-domain data can be transformed into spectral data, and the vibration spectrum corresponding to the vibration data can be obtained.

[0070] Step 203: Determine the sidebands of the target frequency in the vibration spectrum.

[0071] The target frequency is the fault frequency of the bearing component to be diagnosed, which is determined based on empirical values ​​or set by the factory.

[0072] Step 204: Perform fault diagnosis on the bearing components of the gearbox based on the sidebands.

[0073] The gearbox may contain one or more bearing components. Step 204 can perform fault diagnosis on a single bearing component, or it can simultaneously diagnose faults on multiple bearing components based on their transmission relationships. Bearing components may include, but are not limited to, an inner ring, an outer ring, rolling elements, and a cage.

[0074] In one embodiment, fault diagnosis of bearing components can be performed periodically. The shorter the period, the more timely the fault diagnosis of bearing components, the more timely the faults of bearing components can be detected, and the timely countermeasures or fault alerts can be issued.

[0075] In one embodiment, fault diagnosis of bearing components is performed when a trigger condition is met, which can reduce the computational load of fault diagnosis. The trigger condition may include, but is not limited to, the vibration amplitude of the target detection point being greater than an amplitude threshold.

[0076] In this embodiment of the invention, vibration data from the generator and drive shaft are used to diagnose faults in the bearing components of the gearbox. This method is easy to implement and has high accuracy. Even without a speed sensor or with a faulty speed sensor, timely fault diagnosis of the bearing components is possible, ensuring reliability and stability. Furthermore, this method of diagnosing gearbox bearing components based on vibration data eliminates the need for a speed sensor, saving costs.

[0077] In one embodiment, see Figure 3 Step 203 includes the following steps:

[0078] Step 203-1: Determine the vibration frequency corresponding to the largest amplitude value within the range of rotational speed variation in the vibration spectrum.

[0079] When there are multiple target detection points, in step 203-1, the vibration frequency corresponding to the largest amplitude value in the rotational speed change range of the vibration spectrum of each target detection point is determined. That is, when the number of target detection points is n, n vibration frequencies are obtained.

[0080] In one embodiment, the rated speed of the fan is defined as the upper limit of the speed variation range. This method requires no calculation and involves minimal computation.

[0081] In one embodiment, the upper and lower limits of the wind turbine's rotational speed range are determined based on the turbine's historical rotational speed data. This method accurately reflects the wind turbine's operating status with high accuracy.

[0082] It should be noted that the speed variation range can be a fixed range; the speed variation range can also be dynamically adjusted, for example, by acquiring historical speed data once each season and redetermining the speed variation range.

[0083] The vibration frequency corresponding to the maximum amplitude within the rotational speed range is used as the default rotational frequency for each target detection point.

[0084] Step 203-2: Determine the actual rotational frequency of the fan based on the average of at least two vibration frequencies with the smallest deviation.

[0085] If the number of target detection points is n, corresponding to n vibration frequencies, in step 203-2, the deviation between any two vibration frequencies among the n vibration frequencies is calculated, resulting in n*(n-1) / 2 deviation calculation results. The two vibration frequencies corresponding to larger deviations may have interference and cannot accurately reflect the actual operating state of the fan. The two vibration frequencies corresponding to the smallest deviations can generally accurately characterize the actual operating state of the fan. Therefore, the two vibration frequencies corresponding to the smallest deviations are selected, their average value is calculated, and the actual rotational frequency of the fan is determined based on the average value.

[0086] The aforementioned deviations can be characterized, but are not limited to, by difference or ratio.

[0087] Understandably, if both target detection points are deployed on the generator, or on the same drive shaft, or one target detection point is deployed on the generator and the other on a drive shaft directly connected to the generator (e.g., a high-speed shaft), the deviation of the vibration frequencies of the two target detection points can be directly calculated. However, if the two target detection points are not deployed on two directly connected components, then calculating the deviation requires first converting one of the vibration frequencies according to the transmission relationship between the two components before calculating the deviation.

[0088] In this embodiment of the invention, combining different target detection points of different components to jointly determine the actual rotational frequency of the wind turbine can improve the accuracy of the actual rotational frequency determination, thereby improving the accuracy of fault diagnosis. Furthermore, the screening mechanism in steps 203-1 and 203-2 can eliminate interference (such as inaccurate vibration data due to vibration sensor malfunction), improving the accuracy of fault diagnosis.

[0089] Step 203-3: Preprocess the vibration spectrum according to the actual rotation frequency; the preprocessing includes dividing the horizontal axis of the vibration spectrum by the actual rotation frequency.

[0090] The purpose of preprocessing is to facilitate the subsequent determination of the target frequency (fault frequency) in the vibration spectrum.

[0091] Step 203-4: Determine the sidebands of the target frequency in the preprocessed vibration spectrum.

[0092] In one embodiment, before step 203-4, the amplitude corresponding to the generator's electrical frequency in the vibration spectrum is assigned a value of 0, and the sideband of the target frequency in the assigned vibration spectrum is determined. The electrical frequency is a known quantity. It should be noted that the electrical frequency referred to here is related to the AC frequency specified by the location of the wind farm. For example, if the wind farm is located in China, the electrical frequency is equivalent to the AC frequency specified by my country, which is 50Hz.

[0093] The vibration spectrum, after being assigned a value, can eliminate the interference of the fan's electrical frequency on fault diagnosis, thereby improving the accuracy of fault diagnosis.

[0094] In one embodiment, see Figure 4 Step 203 includes the following steps:

[0095] Step 203-5: Determine the center frequency corresponding to the maximum amplitude value within the fault frequency range in the vibration spectrum.

[0096] The fault frequency range is either an empirical value or a factory setting. The fault frequency range can usually identify fault components; that is, when the frequency falls within this range, it indicates a possible fault in the bearing component.

[0097] In one example, the failure frequency range is determined based on bearing parameters and frequently failing bearing components. For example, the bearing inner ring (16.844), outer ring (14.155), rolling elements (11.253), and cage (0.456) are all considered failure frequencies. Generally, the outer and inner rings of the bearing have a higher probability of failure, so the frequency range can vary within 1-3 times the failure frequency range. The failure frequency range can be taken as [14*1, 17*3]. In other words, based on experience, taking approximately 1-3 times the failure frequency can usually help find the failure frequency characteristics and thus determine the failure frequency range.

[0098] The vibration spectrum in step 203-5 can be a vibration spectrum obtained by fast Fourier transform, a vibration spectrum that has been preprocessed, or a vibration spectrum that has been assigned a value.

[0099] Step 203-6: Determine the frequency of the sidebands on both sides of the center frequency in the vibration spectrum.

[0100] Bearing components include inner ring, outer ring, rolling elements, cage, etc. The target frequency is the failure frequency of each bearing component, which is an empirical value or set by the factory.

[0101] Step 203-6 is to find the side frequencies in the vibration spectrum with the center frequency f_max as the center and the side frequencies on the left and right sides of the center frequency f_max, with the fault frequency (target frequency) f_factor of a certain bearing component or its multiples as the interval, and determine the number of the side frequencies i1 and i2, where i1 is the number of the lower side frequency and i2 is the number of the upper side frequency.

[0102] The calculation of the number of times i1 and i2 depends on f_max, the failure frequency f_factor of the bearing component, and the failure frequency range.

[0103] The frequencies i1 and i2 are: i1 = [(f_max - f_lower frequency) / f_factor], and i2 = [(f_upper frequency - f_max) / f_factor]. Here, f_lower frequency is the lower limit of the fault frequency range, and f_upper frequency is the upper limit of the fault frequency range. "[]" represents the floor function. i1 and i2 can be equal or unequal.

[0104] For example, the center frequency f_max corresponding to the maximum amplitude is 10, the fault frequency (target frequency) of the outer ring is 2, and the fault frequency range of the bearing component is 5 to 15, where 5 is the lower sideband and 10 is the upper sideband. Then the order i1 of the lower sideband can be calculated as [(10-5) / 2] = 2, and the order i2 of the upper sideband can be calculated as [(15-10) / 2] = 2.

[0105] Step 203-7: Determine the scope of fault finding based on the number of times.

[0106] In step 203-7, that is, determining the fault search range (f_max-i1*f_factor, f_max+i2*f_factor), the left side of f_max is f_max-i1*factor, and the right side is f_max+i2*factor.

[0107] Step 203-8: Sum the maximum amplitude values ​​within the fault search range in the vibration spectrum.

[0108] In step 203-8, obtain the maximum amplitude within the ±1Hz range of f_max, f_max±factor……f_max±i*factor, where i is i1 or i2.

[0109] Specifically, obtain the maximum amplitude within the range of f_max ± 1Hz, provided that both i1 and i2 are greater than or equal to 1:

[0110] To the left of the center frequency f_max, obtain the maximum amplitude within multiple frequency ranges such as f_max-(1~i1)*f_factor±1HZ;

[0111] To the right of the center frequency f_max, obtain the maximum amplitude within multiple frequency ranges such as f_max+(1~i2)*f_factor±1HZ.

[0112] When i1 is 0, the maximum amplitude within the range of f_max±1HZ is obtained, and the maximum amplitude within the range of f_max+(1~i2)*f_factor±1HZ to the right of the center frequency f_max is summed.

[0113] When i2 is 0, the maximum amplitude within the range of f_max±1HZ is obtained, and the maximum amplitude within the range of f_max-(1~i1)*f_factor±1HZ to the left of the center frequency f_max is summed.

[0114] If i1 and i2 are both 0, then the maximum amplitude within the range of f_max ± 1 Hz is taken as the sum value.

[0115] Finally, all the maximum amplitude values ​​obtained in steps 203-8 are summed, and the summation result is determined as a new indicator for bearing component fault diagnosis.

[0116] For example, when f_max = 10, f_factor = 3.6, and the calculated i1 = 2, i2 = 1:

[0117] To the left of the center frequency f_max, take the maximum amplitude in the relevant range when i=1 and i=2 respectively, that is, the maximum amplitude in the range of (10-1*3.6)±1Hz and (10-2*3.6)±1Hz, that is, the maximum amplitude in the range of 4.4 to 5.4Hz and the maximum amplitude in the range of 1.8 to 3.8Hz.

[0118] To the right of the center frequency f_max, take the maximum amplitude within the relevant range when i=1, that is, the maximum amplitude within the range of (10+1*3.6)±1Hz, which is also the range of 12.6 to 14.6Hz.

[0119] The mean ±1Hz is the allowable error. In practice, the range of this allowable error can be selected as needed. 1Hz is the optimal allowable error range obtained from the research.

[0120] Step 203-9: Perform fault diagnosis on the bearing components based on the summation results.

[0121] If the sum of the results exceeds the preset range, a potential fault is identified in the bearing component, and a fault alert can be issued. If the sum of the results does not exceed the preset range, the bearing component is considered to be operating normally. The preset range is obtained by fitting historical data of the wind turbine's normal operation and represents the range of the sum of results during normal wind turbine operation.

[0122] The summation result represents the fault frequency of the bearing component that can be identified within the fault frequency range and the corresponding amplitude of its harmonics. Using the summation result as a comprehensive index for fault diagnosis of bearing components is easy to implement and has high accuracy.

[0123] In some embodiments, if the indicator shows an upward trend over a period of time, it indicates that the health of the bearings of the wind turbine needs to be checked. In some embodiments, a certain upward trend can correspond to the indicator value increasing as the time axis extends in a time-indicator value coordinate system, or the slope of the straight line connecting two adjacent indicator values ​​in the coordinate system being greater than a preset K value.

[0124] In one embodiment, based on the correspondence between weighted amplitude and fault type, the fault type corresponding to the weighted amplitude that matches the summation result is determined as the fault type of the bearing component.

[0125] For example, the correspondence includes: when the weighted amplitude is 'a', the corresponding fault type is A; when the weighted amplitude is 'b', the corresponding fault type is B; and when the weighted amplitude is 'c', the corresponding fault type is C. If the weighted result obtained in step 203-8 is 'a', then the fault type of the current bearing component can be determined to be A.

[0126] It should be noted that the weighted amplitude can be a single value or a range of values. If a numerical value is used to represent the weighted amplitude, then the two are considered to match if the weighted result is equal to a certain weighted amplitude in the corresponding relationship. If a range of values ​​is used to represent the weighted amplitude, then the two are considered to match if the weighted result falls within a certain range of weighted amplitudes in the corresponding relationship. The specific calculation method for the weighted amplitude is similar to that for the weighted result, and will not be repeated here.

[0127] In one embodiment, the above correspondence is obtained by fitting experimental vibration data and / or historical vibration data corresponding to various fault types.

[0128] In one embodiment, experimental vibration data and / or historical vibration data corresponding to various fault types are used as training samples. The neural network is trained using these training samples, and the trained model is represented as a corresponding relationship.

[0129] The following experimental data further illustrates the fault diagnosis method provided in the embodiments of the present invention.

[0130] Regarding frequency determination: Vibration data from three target detection points in a wind farm—the generator drive end, the generator non-drive end, and the gearbox high-speed shaft perpendicular—were subjected to spectrum conversion. Based on the wind turbine's minimum and rated speeds, the speed variation range [12Hz, 30Hz] was determined. The maximum amplitude of the vibration spectrum at each of the three target detection points within the speed variation range was then searched, and the vibration frequency was found to be 29.5012Hz. Therefore, the wind turbine's timing frequency was confirmed to be 29.5012Hz.

[0131] Vibration data from the target detection point at the non-drive end of a wind farm generator were used for algorithm verification. The severe bearing fault frequency range [0Hz, 950Hz] was selected. After calculation using the fault frequency of the outer ring, it was found that within this fault frequency range, i1 = 6, i2 = 0, and a 6-fold fault frequency sideband can be obtained to the left of the center frequency f_max. The number of sidebands to the right of the center frequency f_max is 0. The final calculation result is as follows: The maximum amplitude within the frequency band calculated by the method provided in any embodiment of the present invention is 28.59356606, which is consistent with the maximum amplitude result of this frequency band in the spectrum data.

[0132] Sideband amplitude results comparison: Calculations show that the left side of the center frequency f_max can be used to calculate the maximum amplitude of the sideband at 6 times the fault frequency within the allowable error range, while the right side can be used to calculate the maximum amplitude of the sideband at 0 times the fault frequency. Compared with the maximum sideband amplitude obtained using the spectrum of existing technologies, it can be seen that the algorithm calculation results of this embodiment are consistent with the sideband amplitude.

[0133] Verification was performed using a horizontal measuring point (target detection point) at the non-drive end of the fan, see [link / reference]. Figure 5 The data for March is fault data, so the indicator is above 1. The data for June is data after the parts were replaced, so the indicator will be below 1. This proves the effectiveness of the embodiments of the present invention.

[0134] Corresponding to the aforementioned embodiments of bearing fault diagnosis methods, the present invention also provides embodiments of bearing fault diagnosis devices.

[0135] Figure 6 This is a schematic diagram of a bearing fault diagnosis device provided as an exemplary embodiment of the present invention. The wind turbine includes a generator and a gearbox, wherein the generator is connected to the drive shaft of the gearbox; the fault diagnosis device includes:

[0136] Applied to a wind turbine system, the wind turbine system including a drive chain, the drive chain including bearing components; the fault diagnosis device includes:

[0137] Acquisition module 51 is used to acquire vibration data of the target detection point on the transmission chain;

[0138] The spectrum determination module 52 is used to determine the vibration spectrum of the target detection point based on the vibration data.

[0139] The frequency band determination module 53 is used to determine the sideband of the target frequency in the vibration spectrum; the target frequency is the fault frequency of the bearing component to be diagnosed.

[0140] The fault diagnosis module 54 is used to perform fault diagnosis on the bearing component based on the sideband.

[0141] Optionally, the frequency band determination module includes:

[0142] A vibration frequency determination unit is used to determine the vibration frequency corresponding to the largest amplitude value within the range of rotational speed change in the vibration spectrum.

[0143] The frequency determination unit is used to determine the actual frequency of the fan based on the average value of at least two vibration frequencies with the smallest deviation;

[0144] A preprocessing unit is used to preprocess the vibration spectrum according to the actual rotation frequency; the preprocessing includes dividing the horizontal axis of the vibration spectrum by the actual rotation frequency;

[0145] The frequency band determination unit is used to determine the sidebands of the target frequency in the preprocessed vibration spectrum.

[0146] Optionally, the frequency band determination module includes:

[0147] An amplitude unit is used to assign a value of 0 to the amplitude corresponding to the electrical frequency of the generator in the vibration spectrum;

[0148] The frequency band determination unit is used to determine the sidebands of the target frequency in the assigned vibration spectrum.

[0149] Optionally, the frequency band determination module includes:

[0150] A center frequency determination unit is used to determine the center frequency corresponding to the maximum amplitude value within the fault frequency range of the vibration spectrum.

[0151] Sideband determination unit, used to determine the sidebands of target frequencies on both sides of the center frequency in the vibration spectrum;

[0152] The fault diagnosis module includes:

[0153] A range determination unit is used to determine the fault search range based on the number of times the sideband is used.

[0154] The summation determination unit is used to sum the maximum amplitude values ​​within the fault search range in the vibration spectrum;

[0155] The fault diagnosis unit is used to diagnose faults in the bearing components based on the summation results.

[0156] Optionally, the fault diagnosis module is specifically used for:

[0157] Based on the correspondence between weighted amplitude and fault type, the fault type corresponding to the weighted amplitude that matches the summation result is determined as the fault type of the bearing component.

[0158] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the present invention according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0159] Figure 7 This is a schematic diagram of the structure of an electronic device according to an example embodiment of the present invention, showing a block diagram of an exemplary electronic device 60 suitable for implementing embodiments of the present invention. Figure 7 The electronic device 60 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0160] like Figure 7As shown, the electronic device 60 can be manifested as a general-purpose computing device, such as a server device. The components of the electronic device 60 may include, but are not limited to: at least one processor 61, at least one memory 62, and a bus 63 connecting different system components (including memory 62 and processor 61).

[0161] Bus 63 includes a data bus, an address bus, and a control bus.

[0162] The memory 62 may include volatile memory, such as random access memory (RAM) 621 and / or cache memory 622, and may further include read-only memory (ROM) 623.

[0163] The memory 62 may also include a program tool 525 (or utility) having a set (at least one) program module 524, such program module 624 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0164] The processor 61 performs various functional applications and data processing, such as the methods provided in any of the above embodiments, by running computer programs stored in the memory 62.

[0165] Electronic device 60 can also communicate with one or more external devices 64 (e.g., keyboard, pointing device, etc.). This communication can be performed via input / output (I / O) interface 65. Furthermore, the model-generated electronic device 60 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public network, such as the Internet) via network adapter 66. As shown, network adapter 66 communicates with other modules of the model-generated electronic device 60 via bus 63. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the model-generated electronic device 60, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems.

[0166] It should be noted that although several units / modules or sub-units / modules of the electronic device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0167] This invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided in any of the above embodiments.

[0168] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0169] In a possible implementation, the present invention can also be implemented as a program product comprising program code, wherein when the program product is run on a terminal device, the program code is used to cause the terminal device to execute the method implementing any of the above embodiments.

[0170] The program code for executing the present invention can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0171] While specific embodiments of the present invention have been described above, those skilled in the art should understand that these are merely illustrative examples, and the scope of protection of the present invention is defined by the appended claims. Those skilled in the art can make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but all such changes and modifications fall within the scope of protection of the present invention.

Claims

1. A method for diagnosing bearing faults, characterized in that, Applied to a wind turbine system, the wind turbine system including a drive chain, the drive chain including bearing components; The fault diagnosis method includes: Obtain vibration data of the target detection point on the transmission chain; The vibration spectrum of the target detection point is determined based on the vibration data; Determine the vibration frequency corresponding to the largest amplitude within the range of rotational speed variation in the vibration spectrum; The actual rotational frequency of the fan is determined based on the average of at least two vibration frequencies with the smallest deviation; Determining the sidebands of the target frequency in the vibration spectrum includes: Determine the center frequency corresponding to the maximum amplitude within the fault frequency range of the vibration spectrum; Determine the sidebands of target frequencies on both sides of the center frequency in the vibration spectrum; the target frequencies are the fault frequencies of the bearing components to be diagnosed. Fault diagnosis of the bearing component based on the sideband includes: The fault location range is determined based on the frequency of the sidebands; Sum the maximum amplitude values ​​within the fault-finding range in the vibration spectrum; The bearing components are then diagnosed based on the summation results.

2. The bearing fault diagnosis method according to claim 1, characterized in that, Determining the sidebands of the target frequency in the vibration spectrum includes: The vibration spectrum is preprocessed based on the actual rotation frequency; the preprocessing includes dividing the horizontal axis of the vibration spectrum by the actual rotation frequency; and determining the sideband of the target frequency in the preprocessed vibration spectrum.

3. The bearing fault diagnosis method according to claim 1, characterized in that, Determining the sidebands of the target frequency in the vibration spectrum includes: The amplitude corresponding to the electrical frequency of the generator in the vibration spectrum is assigned to 0; the sideband of the target frequency in the vibration spectrum after assignment is determined.

4. The bearing fault diagnosis method according to any one of claims 1-3, characterized in that, The fault diagnosis of the bearing component based on the summation result includes: Based on the correspondence between weighted amplitude and fault type, the fault type corresponding to the weighted amplitude that matches the summation result is determined as the fault type of the bearing component.

5. A bearing fault diagnosis device, characterized in that, Applied to a wind turbine system, the wind turbine system including a drive chain, the drive chain including bearing components; the fault diagnosis device includes: The acquisition module is used to acquire vibration data of the target detection point on the transmission chain; A spectrum determination module is used to determine the vibration spectrum of the target detection point based on the vibration data. A vibration frequency determination unit is used to determine the vibration frequency corresponding to the largest amplitude value within the range of rotational speed change in the vibration spectrum. The frequency determination unit is used to determine the actual frequency of the fan based on the average value of at least two vibration frequencies with the smallest deviation; A frequency band determination module is used to determine the sideband of the target frequency in the vibration spectrum; the target frequency is the fault frequency of the bearing component to be diagnosed. The frequency band determination module includes: A center frequency determination unit is used to determine the center frequency corresponding to the maximum amplitude value within the fault frequency range of the vibration spectrum. Sideband determination unit, used to determine the sidebands of target frequencies on both sides of the center frequency in the vibration spectrum; fault diagnosis module, used to perform fault diagnosis on the bearing component based on the sidebands; The fault diagnosis module includes: A range determination unit is used to determine the fault search range based on the number of times the sideband is used. The summation determination unit is used to sum the maximum amplitude values ​​within the fault search range in the vibration spectrum; The fault diagnosis unit is used to diagnose faults in the bearing components based on the summation results.

6. The bearing fault diagnosis device according to claim 5, characterized in that, The frequency band determination module includes: A preprocessing unit is used to preprocess the vibration spectrum according to the actual rotation frequency; the preprocessing includes dividing the horizontal axis of the vibration spectrum by the actual rotation frequency; The frequency band determination unit is used to determine the sidebands of the target frequency in the preprocessed vibration spectrum.

7. The bearing fault diagnosis device according to claim 5, characterized in that, The frequency band determination module includes: An amplitude unit is used to assign a value of 0 to the amplitude corresponding to the electrical frequency of the generator in the vibration spectrum; The frequency band determination unit is used to determine the sidebands of the target frequency in the assigned vibration spectrum.

8. The bearing fault diagnosis device according to claim 5, characterized in that, The fault diagnosis module is specifically used for: Based on the correspondence between weighted amplitude and fault type, the fault type corresponding to the weighted amplitude that matches the summation result is determined as the fault type of the bearing component.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and for running on the processor, characterized in that, When the processor executes the computer program, it implements the bearing fault diagnosis method according to any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the bearing fault diagnosis method according to any one of claims 1 to 4.

Images