Fault early warning method of main bearing and electronic equipment

Abstract

The invention provides a main bearing fault early warning method and electronic equipment. The method comprises the steps that fault diagnosis parameters of a main bearing are acquired, and the fault diagnosis parameters at least comprise vibration signals, rotating speed and fault frequency information of the main bearing; feature extraction is conducted on the fault diagnosis parameters, a multi-feature extraction result is obtained, and the multi-feature extraction result at least comprises time domain features, frequency spectrum features and time domain impact features; and performing fusion analysis on the multi-feature extraction result to obtain a fault judgment result of the main bearing, thereby solving the technical problems that the fault judgment result of the main bearing is relatively low in accuracy and fault misinformation is easy to occur.

Description

Technical Field

[0001] The present application relates to the technical field of wind power generation, and in particular to a main bearing fault warning method and electronic equipment. Background Art

[0002] The main bearing is a key component connecting the wind rotor and the generator. It not only supports and transmits mechanical energy, but also has an important impact on the stability, efficiency and life of the wind turbine. Therefore, it is particularly important to provide early warning for main bearing failures of wind turbines.

[0003] However, in the prior art, in the process of early warning of the main bearing, the early warning of the main bearing is only performed through a single feature analysis, which makes the accuracy of the fault judgment result of the main bearing low and is prone to the problem of false fault alarm. Summary of the invention

[0004] In view of this, the present application provides a main bearing fault warning method and electronic equipment, which solves the technical problem that the main bearing fault judgment result has low accuracy and is prone to false fault alarms.

[0005] As a first aspect of the present application, the present application provides a main bearing fault warning method, comprising: obtaining fault diagnosis parameters of the main bearing, wherein the fault diagnosis parameters at least include the vibration signal, rotational speed and fault frequency information of the main bearing; performing feature extraction on the fault diagnosis parameters to obtain multi-feature extraction results, wherein the multi-feature extraction results at least include time domain features, spectrum features and time domain impact features; performing fusion analysis on the multi-feature extraction results to obtain a main bearing fault judgment result.

[0006] In a possible implementation of the present application, feature extraction is performed on fault diagnosis parameters to obtain multiple feature extraction results, including: preprocessing the fault diagnosis parameters to obtain an envelope spectrum of the main bearing, the envelope spectrum is used to characterize the spectrum analysis results of the envelope of the main bearing vibration signal; based on a preset bandpass filter frequency band, the envelope spectrum is optimized and calculated to obtain a target bandpass filter frequency band, wherein the target bandpass filter frequency band is used to characterize the frequency band corresponding to the identifiable fault frequency in the preset bandpass filter frequency band; the target bandpass filter frequency band is calculated to obtain the fault frequency amplitude corresponding to the main bearing; and the spectrum-like characteristics of the main bearing fault are determined based on the fault frequency amplitude.

[0007] In a possible implementation of the present application, an envelope spectrum is optimized based on a preset bandpass filter frequency band to obtain a target bandpass filter frequency band, including: traversing and calculating the envelope spectrum within the preset bandpass filter frequency band to obtain multiple groups of noise-signal interval indicators, wherein each group of noise-signal interval indicators includes a kurtosis index and a signal-to-noise ratio index; judging whether there are multiple groups of noise-signal interval indicators with a kurtosis index greater than a preset kurtosis parameter, and a signal-to-noise ratio index greater than a preset signal-to-noise ratio parameter; if there are multiple groups of noise-signal interval indicators with a kurtosis index greater than a preset kurtosis parameter, and a signal-to-noise ratio index greater than a preset signal-to-noise ratio parameter, obtaining a corresponding target noise-signal interval indicator; and determining the bandpass filter frequency band corresponding to the target noise-signal interval indicator as the target bandpass filter frequency band.

[0008] In a possible implementation of the present application, an envelope spectrum within a preset bandpass filter frequency band is traversed and calculated to obtain multiple groups of noise-signal interval indicators, including: obtaining a preset fluctuation amplitude of the vibration signal, wherein the preset fluctuation amplitude is determined by the sampling frequency of the vibration signal; obtaining noise interval energy by calculating the fault frequency information of the main bearing and the preset fluctuation amplitude, and determining the noise interval energy as a kurtosis indicator; obtaining the signal interval energy of the main bearing, wherein the signal interval energy is greater than the product of the amplitude corresponding to the fault frequency information multiplied by a preset adjustment ratio; and obtaining a signal-to-noise ratio indicator by performing logarithmic calculation on the signal interval energy and the difference obtained by subtracting the signal interval energy from the noise interval energy.

[0009] In a possible implementation of the present application, a fusion analysis is performed on the results of multi-feature extraction to obtain a fault judgment result of the main bearing, including: judging whether the main bearing is faulty based on the total vibration parameters in the time domain characteristics to obtain a first judgment result; judging whether the main bearing is faulty based on the target bandpass filter frequency band and the fault frequency amplitude in the spectrum characteristics to obtain a second judgment result; judging whether the main bearing is faulty based on the impact period in the time domain impact characteristics to obtain a third judgment result; and performing a fusion analysis on the first judgment result, the second judgment result and the third judgment result to obtain a fault judgment result of the main bearing.

[0010] In a possible implementation of the present application, based on the total vibration parameters in the time domain characteristics, it is determined whether the main bearing is faulty to obtain a first determination result, including: calculating the rising trend of the total vibration parameters in multiple periods to obtain multiple rising trend change rates, wherein the multiple periods include at least short-term, medium-term and long-term; judging whether the multiple rising trend change rates are greater than multiple preset rising rate thresholds, wherein each period in the multiple periods corresponds to a different preset rising rate threshold; if the multiple rising trend change rates are greater than the multiple preset rising rate thresholds, determining that the first determination result is that the main bearing is faulty.

[0011] In a possible implementation of the present application, based on the target bandpass filter frequency band and the fault frequency amplitude in the spectrum-like characteristics, it is determined whether the main bearing has a fault, and a second determination result is obtained, including: based on the target bandpass filter frequency band and the fault frequency amplitude in the spectrum-like characteristics, obtaining the fault frequency of the main bearing within a first preset time period; determining whether the fault frequency is greater than the preset fault frequency; if the fault frequency is greater than the preset fault frequency, determining that the second determination result is that there is a fault in the main bearing.

[0012] In a possible implementation of the present application, based on the impact cycle in the time domain impact-type characteristics, it is determined whether the main bearing has a fault and a third determination result is obtained, including: respectively obtaining a first impact amplitude trend of the impact amplitude corresponding to the impact cycle in the second preset time period, and a second impact amplitude trend of the impact amplitude corresponding to the impact cycle in the third preset time period, wherein the second preset time period is greater than the third preset time period; judging whether the rising trend change rate of the first impact amplitude trend is greater than the first preset rising trend change rate, and whether the falling trend change rate of the second impact amplitude trend is less than the first preset falling trend change rate; if the rising trend change of the first impact amplitude trend is greater than the first preset rising trend change rate, and the falling trend change rate of the second impact amplitude trend is less than the first preset falling trend change rate, it is determined that the third determination result is that the main bearing has a fault.

[0013] In a possible implementation of the present application, the first judgment result, the second judgment result and the third judgment result are fused and analyzed to obtain a fault judgment result of the main bearing, including: judging the target period of the main bearing fault based on the target bandpass filter frequency band in the spectrum-type characteristics; judging the specific damaged part of the main bearing fault based on the fault frequency amplitude in the spectrum-type characteristics and the impact period in the time domain impact-type characteristics.

[0014] As a second aspect of the present application, the present application also provides a main bearing fault warning system, including: an acquisition module, used to obtain fault diagnosis parameters of the main bearing, wherein the fault diagnosis parameters at least include the vibration signal, rotational speed and fault frequency information of the main bearing; an extraction module, used to perform feature extraction on the fault diagnosis parameters to obtain multi-feature extraction results, wherein the multi-feature extraction results at least include time domain features, spectrum features and time domain impact features; an analysis module, used to perform fusion analysis on the multi-feature extraction results to obtain a fault judgment result of the main bearing.

[0015] As a third aspect of the present application, the present application further provides an electronic device, which stores computer program information. When the computer program information is executed by a processor, the processor executes any one of the main bearing fault warning methods mentioned above.

[0016] As a fourth aspect of the present application, the present application further provides a computer-readable storage medium, the storage medium storing a computer program, and the computer program is used to execute any of the above-mentioned main bearing fault warning methods.

[0017] The main bearing fault warning method provided by the present application includes: obtaining the fault diagnosis parameters of the main bearing, wherein the fault diagnosis parameters at least include the vibration signal, rotation speed and fault frequency information of the main bearing; performing feature extraction on the fault diagnosis parameters to obtain multi-feature extraction results, wherein the multi-feature extraction results at least include time domain features, spectrum features and time domain impact features; performing fusion analysis on the multi-feature extraction results to obtain the fault determination result of the main bearing. It is easy to notice that the present application realizes multi-feature fusion warning by fusion analysis of the extracted time domain features, spectrum features and time domain impact features, so as to obtain the fault determination result of the main bearing more accurately, thereby achieving the technical effect of improving the accuracy of the fault determination result of the main bearing, thereby avoiding false fault reports, thereby solving the technical problem that the fault determination result accuracy of the main bearing is low and false fault reports are prone to occur. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0019] Figure 1 Shown is a flow chart of a main bearing fault warning method provided in one embodiment of the present application.

[0020] Figure 2 The flowchart shown is a method for automatically optimizing the optimal filtering frequency band based on the signal-to-noise ratio and kurtosis provided by an embodiment of the present application.

[0021] Figure 3 The figure shows a flow chart for judging the early, middle and late stage degradation state of a main bearing failure provided by an embodiment of the present application.

[0022] Figure 4 Shown is a schematic diagram of a main bearing fault warning system provided in an embodiment of the present application.

[0023] Figure 5 Shown is a device block diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0024] In the description of the application, the meaning of "multiple" is at least two, for example, two, three, etc., unless otherwise clearly and specifically limited. In the embodiment of the present application, all directional indications (such as up, down, left, right, front, back, top, bottom ...) are only used to explain the relative position relationship, motion conditions, etc. between the components under a certain specific posture (as shown in the drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their deformations are intended to cover non-exclusive inclusions. For example, the process, method, system, product or equipment comprising a series of steps or units are not limited to the steps or units listed, but optionally also include the steps or units not listed, or optionally also include other steps or units inherent to these processes, methods, products or equipment.

[0025] In addition, the reference to "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0026] Exemplary Methods

[0027] As a first aspect of the present application, the present application provides a main bearing fault early warning method. Figure 1 FIG. 1 is a flow chart of a main bearing fault warning method provided by an embodiment of the present application, as shown in FIG. Figure 1 As shown, the method comprises the following steps:

[0028] S101, acquiring fault diagnosis parameters of the main bearing, wherein the fault diagnosis parameters at least include a vibration signal, a rotation speed, and fault frequency information of the main bearing;

[0029] Specifically, the above fault diagnosis parameters can be used to represent parameters for fault detection of the main bearing of the wind turbine. Generally, the fault diagnosis parameters at least include time domain characteristic parameters and frequency domain characteristic parameters.

[0030] The above-mentioned vibration signal includes characteristics such as amplitude, frequency and phase. Generally, a piezoelectric acceleration sensor can be arranged near the main shaft bearing seat of the wind turbine set to pick up the original vibration signal generated during the operation of the set.

[0031] The above speed refers to the rotation speed of the main shaft. In a wind turbine, the speed is directly related to the rotation of the wind rotor. Generally, wind turbines are usually equipped with special speed sensors, which can be installed at the input end of the generator, the output end of the gearbox and the wind rotor speed. These sensors can directly measure the speed and provide accurate data.

[0032] The above fault frequency information refers to specific frequency components related to bearing faults, which are usually caused by physical damage or abnormalities inside the bearing. These frequency components can be identified through vibration analysis. Generally, vibration response is tested by adding vibration sensors (usually acceleration sensors) to the bearing seat or support structure, and the bearing is diagnosed and analyzed using time domain and frequency domain methods. The calculation of fault frequency usually includes: inner ring fault frequency, outer ring fault frequency, rolling element fault frequency, and cage fault frequency.

[0033] In an optional embodiment, during the fault warning process of the main bearing, it is first necessary to obtain the fault diagnosis parameters of the main bearing, including but not limited to obtaining the vibration signal, rotation speed and fault frequency information of the main bearing, etc. Specifically, the vibration signal can be monitored by a piezoelectric acceleration sensor installed near the main shaft bearing seat of the wind turbine, the rotation speed can be monitored by a rotation speed sensor installed at the input end of the generator, the output end of the gear box and the wind rotor speed, and the fault frequency information can be monitored by a vibration sensor installed on the bearing seat or the supporting structure.

[0034] S102, performing feature extraction on the fault diagnosis parameters to obtain a multi-feature extraction result, wherein the multi-feature extraction result at least includes a time domain feature, a spectrum feature, and a time domain impact feature;

[0035] Specifically, the above-mentioned time domain features are the most commonly used monitoring parameters in the vibration monitoring of the main bearings of wind turbines, and can effectively capture the bearing faults of wind turbines. When the main bearing fails, the vibration amplitude will increase significantly and generate an impact signal. These features include the vibration amplitude change trend (mean), vibration energy size (variance), vibration intensity (mean square value), kurtosis, peak value, and pulse index. These parameters have different sensitivities to the identification of early bearing faults. For example, the kurtosis and peak indexes are very sensitive to small impacts and can be used for early bearing fault diagnosis.

[0036] The above-mentioned spectrum characteristics transform the time domain vibration signal into the frequency domain vibration signal through Fourier transform. The spectrum can directly reflect the energy size, frequency composition and phase of the vibration signal. Frequency domain analysis is the most commonly used vibration analysis method, which is performed through Fourier transform or envelope demodulation spectrum analysis. The identification of fault characteristic frequencies in the frequency domain is crucial, because the fault characteristics of rolling bearings are usually manifested as modulation phenomena, and the time domain waveform of the vibration signal is relatively complex, which cannot directly express the fault signal characteristics.

[0037] The above-mentioned time-domain impact features mainly focus on the impact signals in the vibration signal, which are usually related to bearing failures. For example, by comparing the pulse-to-frequency ratio of the time-domain signal with the failure frequency of the rolling element, the rolling element failure can be determined. Acceleration envelope analysis can identify the fault characteristic frequency in the frequency domain signal spectrum, which is particularly effective for high-frequency impact vibration. The analysis of time-domain impact features can be performed by using the Teager energy operator to perform envelope demodulation analysis on the deconvoluted signal, and the fault location of the main bearing of the wind turbine can be accurately determined by the spectral lines with prominent amplitudes in the envelope spectrum.

[0038] In an optional embodiment, after the fault diagnosis parameters of the main bearing are obtained, feature extraction can be performed on the fault diagnosis parameters to obtain extraction results of the main bearing in terms of time domain features, spectrum features, and time domain impact features. Specifically, in the process of obtaining time domain features, the total vibration trend of the main bearing in the short, medium, and long term stages can be obtained to determine whether the main bearing is abnormal based on the total vibration trend; in the process of obtaining spectrum features, the fault frequency amplitude and bandpass filter frequency band of the main bearing can be obtained to determine whether the main bearing is abnormal; in the process of obtaining time domain alluvial features, the impact amplitude and impact period of the main bearing can be obtained to determine whether the main bearing is abnormal.

[0039] It should be noted that in the process of obtaining spectral features, after converting the time domain data to the frequency domain through Fourier transform, the optimal filtering frequency band is automatically optimized based on the signal-to-noise ratio and kurtosis. The fault frequency can be identified in the optimal filtering frequency band, and then the amplitude and signal-to-noise ratio of the fault frequency are calculated, and the current filtering frequency band is used as the spectral feature.

[0040] S103, performing fusion analysis on the multi-feature extraction results to obtain a fault determination result of the main bearing.

[0041] Specifically, after obtaining the multi-feature extraction results, a fusion analysis can be performed based on the first judgment result obtained by the time domain features, the second judgment result obtained by the spectrum features, and the third judgment result obtained by the time domain alluvial features to obtain the fault judgment result of the main bearing.

[0042] In an optional embodiment, during the fusion analysis process, illustratively, after determining that the main bearing is abnormal through spectrum-type features, the period of the main bearing fault can be determined through the current bandpass filter frequency band, that is, if the current bandpass filter frequency band is in a low-frequency state, the corresponding main bearing fault is in a late stage; after determining that the main bearing is abnormal through time-domain impact-type features, the impact cycle can be used to assist in determining the specific damaged part of the main bearing, that is, when the impact cycle presents a short-term downward trend, it can be comprehensively determined that the main bearing is in a late stage of fault, and at the same time, if it is identified through spectrum-type features that the main bearing currently meets the inner ring fault frequency, it is confirmed that the main bearing has an inner ring fault, and the inner ring fault is in a late stage; after determining that the main bearing is abnormal through time-domain features, if the total vibration trend is in an upward trend for a long period of time, it is determined that the main bearing fault is in a late stage, etc.

[0043] In summary, in the process of fusion analysis of multi-feature extraction results, judgment can be made based on the specific working conditions of the above-mentioned vibration signals. By performing multi-feature fusion analysis, a more precise judgment can be made on the fault period and specific damage location of the main bearing.

[0044] The main bearing fault warning method provided by the present application includes: obtaining the fault diagnosis parameters of the main bearing, wherein the fault diagnosis parameters at least include the vibration signal, rotation speed and fault frequency information of the main bearing; performing feature extraction on the fault diagnosis parameters to obtain multi-feature extraction results, wherein the multi-feature extraction results at least include time domain features, spectrum features and time domain impact features; performing fusion analysis on the multi-feature extraction results to obtain the fault determination result of the main bearing. It is easy to notice that the present application realizes multi-feature fusion warning by fusion analysis of the extracted time domain features, spectrum features and time domain impact features, so as to obtain the fault determination result of the main bearing more accurately, thereby achieving the technical effect of improving the accuracy of the fault determination result of the main bearing, thereby avoiding false fault reports, thereby solving the technical problem that the fault determination result accuracy of the main bearing is low and false fault reports are prone to occur.

[0045] In a possible implementation of the present application, feature extraction is performed on fault diagnosis parameters to obtain multiple feature extraction results, including: preprocessing the fault diagnosis parameters to obtain an envelope spectrum of the main bearing, the envelope spectrum is used to characterize the spectrum analysis results of the envelope of the main bearing vibration signal; based on a preset bandpass filter frequency band, the envelope spectrum is optimized and calculated to obtain a target bandpass filter frequency band, wherein the target bandpass filter frequency band is used to characterize the frequency band corresponding to the identifiable fault frequency in the preset bandpass filter frequency band; the target bandpass filter frequency band is calculated to obtain the fault frequency amplitude corresponding to the main bearing; and the spectrum-like characteristics of the main bearing fault are determined based on the fault frequency amplitude.

[0046] Specifically, the above-mentioned preset bandpass filter frequency band can be used to represent multiple pre-set bandpass filter frequency bands, exemplarily, it can be 20-60 Hz, 50-100 Hz, 500-1000 Hz, etc. The preset bandpass filter frequency band is not specifically set here and can be adjusted according to actual conditions.

[0047] Generally, since the frequency domain characteristics of the faulty bearing signal are usually smaller in amplitude than the characteristic values ​​of the normal bearing signal, it is possible to determine whether the main bearing is abnormal by calculating the fault frequency amplitude corresponding to the main bearing.

[0048] In an optional embodiment, during the preprocessing of the fault diagnosis parameters, a series of bandpass filter frequency bands can be given in advance, namely the above-mentioned preset bandpass filter frequency bands, and then the acquired fault diagnosis parameters are preprocessed by bandpass filtering, envelope demodulation, etc., and the envelope spectrum of the main bearing can be obtained, and then the envelope spectrum is optimized based on the preset bandpass filter frequency band to obtain the target bandpass filter frequency band, and the fault frequency of the main bearing can be identified in the target bandpass filter frequency band. After obtaining the target bandpass filter frequency band, the fault frequency amplitude of the main bearing can be calculated according to the target bandpass filter frequency band, so as to determine the spectrum characteristics of the main bearing fault.

[0049] In another optional embodiment, during the optimization calculation of the envelope spectrum based on a preset bandpass filter frequency band, two indicators, signal-to-noise ratio and kurtosis, can be calculated to automatically optimize the optimal filter frequency band that can identify the fault frequency, that is, the above-mentioned target bandpass filter frequency band.

[0050] In a possible implementation of the present application, an envelope spectrum is optimized based on a preset bandpass filter frequency band to obtain a target bandpass filter frequency band, including: traversing and calculating the envelope spectrum within the preset bandpass filter frequency band to obtain multiple groups of noise-signal interval indicators, wherein each group of noise-signal interval indicators includes a kurtosis index and a signal-to-noise ratio index; judging whether there are multiple groups of noise-signal interval indicators with a kurtosis index greater than a preset kurtosis parameter, and a signal-to-noise ratio index greater than a preset signal-to-noise ratio parameter; if there are multiple groups of noise-signal interval indicators with a kurtosis index greater than a preset kurtosis parameter, and a signal-to-noise ratio index greater than a preset signal-to-noise ratio parameter, obtaining a corresponding target noise-signal interval indicator; and determining the bandpass filter frequency band corresponding to the target noise-signal interval indicator as the target bandpass filter frequency band.

[0051] Specifically, the above kurtosis index describes the degree to which the vibration signal deviates from Gaussian at the frequency. The spectral kurtosis of the frequency band dominated by transient impact signals is large, while the spectral kurtosis of the frequency band dominated by stable Gaussian background noise signals is small.

[0052] Generally, when the bearing is working normally, the amplitude of the vibration signal is close to the normal distribution, and the kurtosis index K is about 3. As the bearing runs, the bearing begins to fail. At this time, there is an impact signal in the time domain, the kurtosis curve deviates, and no longer satisfies the normal distribution. The kurtosis index is greater than the initial value of 3; the larger the kurtosis index, the more serious the bearing damage.

[0053] The above signal-to-noise ratio index reflects the clarity of the vibration signal against the noise background.

[0054] Generally, the higher the signal-to-noise ratio, the more prominent the useful information in the signal is, and the easier it is to extract from the noise. The signal-to-noise ratio is very important for bearing fault diagnosis, especially in the case of low signal-to-noise ratio, the fault characteristics may be masked by background noise, making the fault difficult to diagnose. Improving the signal-to-noise ratio can more effectively extract fault information and perform early fault diagnosis.

[0055] The above-mentioned preset kurtosis parameter can be used to represent a preset parameter value for determining the kurtosis index, which can be 3 or 4, etc. The preset kurtosis parameter is not specifically set here and can be adjusted according to actual conditions.

[0056] The above-mentioned preset signal-to-noise ratio parameter can be used to represent a preset parameter value for determining the signal-to-noise ratio index, which can be 6 or 8, etc. The preset signal-to-noise ratio parameter is not specifically set here and can be adjusted according to actual conditions.

[0057] In an optional embodiment, in the process of optimizing the envelope spectrum based on the preset bandpass filter frequency band to obtain the target bandpass filter frequency band, the envelope spectrum within the preset bandpass filter frequency band can be traversed and calculated, that is, the envelope spectrum within each group of bandpass filter frequency bands is calculated, and the kurtosis index and signal-to-noise ratio index of the vibration signal in each group of bandpass filter frequency bands are obtained in turn, and then it is judged in turn whether the kurtosis index of the vibration signal in each group of bandpass filter frequency bands is greater than the preset kurtosis parameter, and whether the signal-to-noise ratio index is greater than the preset signal-to-noise ratio parameter. If the kurtosis index is greater than the preset kurtosis parameter, and the signal-to-noise ratio index is greater than the preset signal-to-noise ratio parameter, it indicates that an abnormality may be detected in the main bearing in this group of bandpass filter frequency bands, and therefore the bandpass filter frequency band corresponding to the target noise-signal interval index is determined as the target bandpass filter frequency band.

[0058] In a possible implementation of the present application, an envelope spectrum within a preset bandpass filter frequency band is traversed and calculated to obtain multiple groups of noise-signal interval indicators, including: obtaining a preset fluctuation amplitude of the vibration signal, wherein the preset fluctuation amplitude is determined by the sampling frequency of the vibration signal; obtaining noise interval energy by calculating the fault frequency information of the main bearing and the preset fluctuation amplitude, and determining the noise interval energy as a kurtosis indicator; obtaining the signal interval energy of the main bearing, wherein the signal interval energy is greater than the product of the amplitude corresponding to the fault frequency information multiplied by a preset adjustment ratio; and obtaining a signal-to-noise ratio indicator by performing logarithmic calculation on the signal interval energy and the difference obtained by subtracting the signal interval energy from the noise interval energy.

[0059] Specifically, in the process of determining the noise interval energy of the main bearing, it can be obtained by adjusting the fluctuation frequency of the acquired fault frequency of the main bearing. The above-mentioned preset fluctuation amplitude can be determined by the sampling frequency of the vibration signal. For example, if the sampling frequency of the vibration signal is 5000 Hz, the fluctuation frequency can be 0.5 Hz, etc.

[0060] In an optional embodiment, the envelope spectrum within the preset bandpass filter frequency band is traversed and calculated to obtain multiple groups of noise-signal interval indicators. The preset fluctuation amplitude of the vibration signal can be obtained based on the sampling frequency of the vibration signal, and then the preset fluctuation amplitude can be added or subtracted by the fault frequency information of the main bearing to obtain the above-mentioned kurtosis index. Among them, a small interval near the frequency corresponding to the fault frequency of the main bearing can be calculated, and the general interval length f1~f2 Hz is used as the noise interval. Generally, the noise interval energy = fault frequency information ± (f1~f2) Hz.

[0061] In the process of calculating the signal-to-noise ratio index, a small interval that satisfies w% of the amplitude corresponding to the main bearing fault frequency can be selected as the signal interval, and the kurtosis index can be calculated using the noise interval. Generally, the signal interval energy = the small interval near the fault frequency that satisfies the amplitude corresponding to the fault frequency * W1%. After calculating the signal interval energy, the signal interval energy and the difference between the noise interval energy and the signal interval energy can be logarithmically calculated, such as: log(signal interval energy / (noise interval energy-signal interval energy)).

[0062] Figure 2 FIG. 1 is a flowchart of automatically optimizing the optimal filtering frequency band based on the signal-to-noise ratio and kurtosis provided by an embodiment of the present application. Figure 2 As shown, including:

[0063] Based on the acquired vibration signal, rotation speed and fault frequency, the square of the envelope spectrum amplitude is calculated and divided by the frequency resolution corresponding to the vibration signal, instead of directly using the envelope spectrum for subsequent calculations to suppress noise;

[0064] Traverse all filter frequency bands;

[0065] Calculate the noise interval energy separately: fault frequency information ±(f1~f2)Hz; signal interval energy: a small interval near the fault frequency that satisfies the corresponding amplitude of the fault frequency *W1%;

[0066] Determine the kurtosis index based on the energy of the noise interval;

[0067] Determine the signal-to-noise ratio index based on the signal interval energy, that is, signal-to-noise ratio = log (signal interval energy / (noise interval energy-signal interval energy));

[0068] Determine whether the signal-to-noise ratio index is greater than a preset signal-to-noise ratio parameter s, and whether the kurtosis index is greater than a preset kurtosis parameter k;

[0069] If the signal-to-noise ratio index is greater than the preset signal-to-noise ratio parameter s, and the kurtosis index is greater than the preset kurtosis parameter k, the target band-pass filter frequency band corresponding to the fault frequency is identified; if the signal-to-noise ratio index is not greater than the preset signal-to-noise ratio parameter s, and the kurtosis index is greater than the preset kurtosis parameter k, the target band-pass filter frequency band corresponding to the fault frequency is identified, then jump to "traverse all filter frequency bands" and perform the next loop until all filter frequency bands are traversed, the loop ends, and the fault frequency is not identified.

[0070] In a possible implementation of the present application, a fusion analysis is performed on the results of multi-feature extraction to obtain a fault judgment result of the main bearing, including: judging whether the main bearing is faulty based on the total vibration parameters in the time domain characteristics to obtain a first judgment result; judging whether the main bearing is faulty based on the target bandpass filter frequency band and the fault frequency amplitude in the spectrum characteristics to obtain a second judgment result; judging whether the main bearing is faulty based on the impact period in the time domain impact characteristics to obtain a third judgment result; and performing a fusion analysis on the first judgment result, the second judgment result and the third judgment result to obtain a fault judgment result of the main bearing.

[0071] Specifically, in an optional embodiment, in the process of performing a fusion analysis on the feature extraction results to obtain the fault judgment result of the main bearing, the time domain features, spectrum features and time domain impact features can be judged one by one to obtain a first judgment result corresponding to the time domain features, a second judgment result corresponding to the spectrum features and a third judgment result corresponding to the time domain impact features, and then the first judgment result, the second judgment result and the third judgment result are fused and analyzed to obtain the fault judgment result of the main bearing.

[0072] In a possible implementation of the present application, based on the total vibration parameters in the time domain characteristics, it is determined whether the main bearing is faulty to obtain a first determination result, including: calculating the rising trend of the total vibration parameters in multiple periods to obtain multiple rising trend change rates, wherein the multiple periods include at least short-term, medium-term and long-term; judging whether the multiple rising trend change rates are greater than multiple preset rising rate thresholds, wherein each period in the multiple periods corresponds to a different preset rising rate threshold; if the multiple rising trend change rates are greater than the multiple preset rising rate thresholds, determining that the first determination result is that the main bearing is faulty.

[0073] Specifically, in the process of determining whether the main bearing is faulty based on the total vibration parameters in the time domain characteristics and obtaining the first determination result, the rising trend of the total vibration parameters in multiple periods can be calculated to obtain multiple rising trend change rates, wherein the above-mentioned multiple periods can be divided into short-term, medium-term and long-term, respectively, and then determine whether the multiple rising trend change rates are greater than multiple preset rising rate thresholds, that is, determine whether the rising trend change rates in different periods are greater than the corresponding preset rising rate thresholds. For example, it can be determined whether the rising trend change rate of the short-term d1 is greater than the first preset rising rate threshold a1, whether the rising trend change rate of the medium-term d2 is greater than the second preset rising rate threshold a2, and whether the rising trend change rate of the long-term d3 is greater than the third preset rising rate threshold a3. If the multiple rising trend change rates are greater than the multiple preset rising rate thresholds, then the first determination result is determined to be that the main bearing is faulty.

[0074] It should be noted that in order to avoid the problem of false alarm of the main bearing, the total vibration trend is divided into periods in the present application, that is, it is necessary to judge whether the rising trend change rate of the short, medium and long periods is greater than the corresponding preset rising rate threshold, thereby achieving a more precise determination of whether the main bearing has a fault, thereby avoiding false alarm of the main bearing.

[0075] In a possible implementation of the present application, based on the target bandpass filter frequency band and the fault frequency amplitude in the spectrum-like characteristics, it is determined whether the main bearing has a fault, and a second determination result is obtained, including: based on the target bandpass filter frequency band and the fault frequency amplitude in the spectrum-like characteristics, obtaining the fault frequency of the main bearing within a first preset time period; determining whether the fault frequency is greater than the preset fault frequency; if the fault frequency is greater than the preset fault frequency, determining that the second determination result is that there is a fault in the main bearing.

[0076] Specifically, the first preset time period mentioned above can be used to represent a preset short-term cycle, but it should be noted that the first preset time period is different from the short-term in the above multiple periods.

[0077] The above-mentioned fault frequency can be used to indicate the number of occurrences of fault frequencies in different bandpass filter frequency bands identified in a short period of time.

[0078] The above-mentioned preset fault frequency can be used to represent a preset short-term fault frequency threshold. The preset fault frequency is not specifically set here and can be adjusted according to actual conditions.

[0079] In an optional embodiment, in the process of determining whether the main bearing has a fault based on the target bandpass filter frequency band and the fault frequency amplitude in the spectrum-like feature and obtaining the second determination result, the fault frequency of the main bearing in the first preset time period can be obtained, and then it can be determined whether the fault frequency is greater than the preset fault frequency. If the fault frequency is greater than the preset fault frequency, the second determination result is determined to be that the main bearing has a fault. Exemplarily, by judging the number of fault frequencies identified in a short period of time, if the number of fault frequencies identified in a short period of time> the preset fault frequency, it is considered that the main bearing has a fault. For example, if the number of fault frequencies identified in the past 30 days> 30 times, it is considered that there is a fault. If only one fault frequency is identified in the past 30 days, it is considered normal.

[0080] In a possible implementation of the present application, based on the impact cycle in the time domain impact-type characteristics, it is determined whether the main bearing has a fault and a third determination result is obtained, including: respectively obtaining a first impact amplitude trend of the impact amplitude corresponding to the impact cycle in the second preset time period, and a second impact amplitude trend of the impact amplitude corresponding to the impact cycle in the third preset time period, wherein the second preset time period is greater than the third preset time period; judging whether the rising trend change rate of the first impact amplitude trend is greater than the first preset rising trend change rate, and whether the falling trend change rate of the second impact amplitude trend is less than the first preset falling trend change rate; if the rising trend change of the first impact amplitude trend is greater than the first preset rising trend change rate, and the falling trend change rate of the second impact amplitude trend is less than the first preset falling trend change rate, it is determined that the third determination result is that the main bearing has a fault.

[0081] Specifically, the second preset time period mentioned above can be used to represent a preset long-term period.

[0082] The third preset time period mentioned above can be used to represent a preset short-term period.

[0083] It should be noted that the second preset period and the third preset period are different from any of the long term or short term mentioned above.

[0084] In the calculation of time domain impact characteristics, the vibration signal is high-pass filtered to obtain the filtered time domain waveform, which is divided into several time segments according to the time length T, and the maximum value of each time segment is calculated. After all values ​​of the time segment are replaced with the maximum value, the envelope demodulation is performed using the Hilbert change method to obtain the envelope spectrum. The spindle rotation frequency, fault frequency, etc. in the envelope spectrum are identified, and the one with the largest amplitude is selected as the impact interval. According to the impact interval / impact period, the corresponding impact amplitude in the time domain waveform is calculated.

[0085] In an optional embodiment, in the process of determining whether the main bearing is faulty based on the impact cycle in the time domain impact-type characteristics and obtaining the third determination result, the first impact amplitude trend of the impact amplitude corresponding to the impact cycle in the second preset time period d5 and the second impact amplitude trend of the impact amplitude corresponding to the impact cycle in the third preset time period d6 can be obtained respectively, and then it is determined whether the rising trend change rate of the first impact amplitude trend is greater than the first preset rising trend change rate a5, and whether the falling trend change rate of the second impact amplitude trend is less than the first preset falling trend change rate a6. If the rising trend change of the first impact amplitude trend is greater than the first preset rising trend change rate a5, and the falling trend change rate of the second impact amplitude trend is less than the first preset falling trend change rate a6, then the third determination result is determined to be that the main bearing is faulty.

[0086] In summary, by obtaining the long-term and short-term shock amplitude trends and judging whether the long-term shock amplitude trend has an upward trend and whether the short-term shock amplitude trend has a downward trend, the problem of shock false alarms can be effectively reduced.

[0087] In a possible implementation of the present application, the first judgment result, the second judgment result and the third judgment result are fused and analyzed to obtain a fault judgment result of the main bearing, including: judging the target period of the main bearing fault based on the target bandpass filter frequency band in the spectrum-type characteristics; judging the specific damaged part of the main bearing fault based on the fault frequency amplitude in the spectrum-type characteristics and the impact period in the time domain impact-type characteristics.

[0088] Specifically, the above-mentioned target period can be used to indicate the period when the main bearing is faulty, which can be early, middle or late. The target period is not specifically determined here, but can be determined by the target bandpass filter frequency band in the spectrum-type characteristics.

[0089] The above-mentioned specific damaged parts can be used to indicate the specific parts where the main bearing has a fault, which may be the inner ring, the outer ring, the rolling element, etc.

[0090] In an optional embodiment, the first determination result, the second determination result and the third determination result are fused and analyzed to obtain the fault determination result of the main bearing. If the first determination result, the second determination result and the third determination result all show that the main bearing is faulty, the total vibration parameters in the time domain characteristics, the target bandpass filter frequency band and the fault frequency amplitude in the spectrum characteristics and the impact period in the time domain impact characteristics can be fused and analyzed to determine the target period of the main bearing failure and the specific damage location.

[0091] Specifically, the target period of main bearing fault can be determined based on the target bandpass filter frequency band in the spectrum characteristics. That is, when the target bandpass filter frequency band is at a low frequency, the corresponding target period of main bearing fault is at a late stage; conversely, when the target bandpass filter frequency band is at a high frequency, the corresponding target period of main bearing fault is at an early stage.

[0092] At the same time, the specific damaged part of the main bearing can also be judged based on the fault frequency amplitude in the spectrum characteristics and the impact cycle in the time domain impact characteristics. Since the frequency amplitude of the vibration signal is different when each part of the main bearing is damaged, the fault frequency amplitude in the spectrum characteristics and the impact cycle in the time domain impact characteristics can be used for auxiliary judgment to determine the specific damaged part of the main bearing. For example, if the identified fault frequency amplitude corresponds to the outer ring fault frequency, and the impact cycle is also an impact with the outer ring fault frequency as the interval, then the outer ring of the main bearing may be faulty.

[0093] In summary, by fusing and analyzing the total vibration parameters in the time domain features, the target bandpass filter frequency band and fault frequency amplitude in the spectrum features, and the impact period in the time domain impact features, the target period of main bearing failure and the specific damage location can be determined more accurately.

[0094] Figure 3 FIG. 1 is a flow chart of judging the early, middle and late stage degradation state of a main bearing failure provided by an embodiment of the present application, as shown in FIG. Figure 3 As shown, including:

[0095] Perform Fourier transformation on the acquired vibration signal, rotation speed and fault frequency to obtain spectrum information;

[0096] Extract time-domain features from spectrum information to obtain total vibration / effective value;

[0097] Extract spectrum features from spectrum information to obtain fault frequency amplitude and bandpass filter frequency band;

[0098] That is, the spectrum is transformed through Hilbert transform and bandpass filtering to obtain the envelope spectrum, and the spectrum-like features are extracted based on the envelope spectrum.

[0099] Extract time-domain impact features from the spectrum information to obtain the impact period and impact interval / period;

[0100] That is, the spectrum is transformed through Hilbert transform, high-pass filtering, and window calculation of peak values ​​to obtain the envelope spectrum, and the spectrum-like features are extracted based on the envelope spectrum.

[0101] Based on the time domain characteristics, calculate whether the rising trend of short-, medium- and long-term data reaches the threshold. If so, it is determined that the main bearing is faulty, and the first judgment result is obtained;

[0102] Based on the spectrum characteristics, it is determined whether the frequency of occurrence of the short-term fault frequency characteristics reaches a threshold value. If so, it is determined that the main bearing has a fault, and a second judgment result is obtained;

[0103] Based on the time domain impact characteristics, it is determined whether the long-term upward trend reaches the threshold and whether a short-term downward trend occurs. If so, it is determined that the main bearing is faulty, and a third judgment result is obtained;

[0104] Based on the first judgment result, the second judgment result and the third judgment result, a multi-feature fusion warning is performed to judge the early, middle and late degradation status of the main bearing.

[0105] Exemplary Systems

[0106] As a second aspect of the present application, the present application also provides a main bearing fault warning system. Figure 4 FIG. 1 is a schematic diagram of a main bearing fault warning system provided by an embodiment of the present application. Figure 4 As shown, the system includes:

[0107] An acquisition module 401 is used to acquire fault diagnosis parameters of the main bearing, wherein the fault diagnosis parameters at least include a vibration signal, a rotation speed and fault frequency information of the main bearing;

[0108] An extraction module 402 is used to perform feature extraction on the fault diagnosis parameters to obtain a multi-feature extraction result, wherein the multi-feature extraction result at least includes time domain features, spectrum features, and time domain impact features;

[0109] The analysis module 403 is used to perform fusion analysis on the multi-feature extraction results to obtain the fault determination result of the main bearing.

[0110] In a possible implementation of the present application, the extraction module includes: a preprocessing module, which is used to preprocess the fault diagnosis parameters to obtain the envelope spectrum of the main bearing, and the envelope spectrum is used to characterize the spectrum analysis results of the envelope of the main bearing vibration signal; an optimization calculation module, which is used to perform optimization calculation on the envelope spectrum based on a preset bandpass filter frequency band to obtain a target bandpass filter frequency band, wherein the target bandpass filter frequency band is used to characterize the frequency band corresponding to the identifiable fault frequency in the preset bandpass filter frequency band; a frequency band calculation module, which is used to calculate the target bandpass filter frequency band to obtain the fault frequency amplitude corresponding to the main bearing; and determine the spectrum-like characteristics of the main bearing fault based on the fault frequency amplitude.

[0111] In a possible implementation of the present application, the optimization calculation module includes: a traversal module, which is used to perform traversal calculations on the envelope spectrum within a preset bandpass filter frequency band to obtain multiple groups of noise-signal interval indicators, wherein each group of noise-signal interval indicators includes a kurtosis index and a signal-to-noise ratio index; a first judgment module, which is used to judge whether there are multiple groups of noise-signal interval indicators with a kurtosis index greater than a preset kurtosis parameter, and a signal-to-noise ratio index greater than a preset signal-to-noise ratio parameter; a target interval indicator acquisition module, which is used to obtain the corresponding target noise-signal interval indicator if there are multiple groups of noise-signal interval indicators with a kurtosis index greater than a preset kurtosis parameter, and a signal-to-noise ratio index greater than a preset signal-to-noise ratio parameter; a target filter frequency band determination module, which is used to determine the bandpass filter frequency band corresponding to the target noise-signal interval indicator as the target bandpass filter frequency band.

[0112] In a possible implementation of the present application, the traversal module includes: a preset fluctuation amplitude acquisition module, which is used to acquire a preset fluctuation amplitude of a vibration signal, wherein the preset fluctuation amplitude is determined by a sampling frequency of the vibration signal; a kurtosis acquisition module, which is used to obtain a noise interval energy by calculating the fault frequency information of the main bearing and the preset fluctuation amplitude, and determine the noise interval energy as a kurtosis index; a signal interval energy acquisition module, which is used to acquire the signal interval energy of the main bearing, wherein the signal interval energy is greater than the product obtained by multiplying the amplitude corresponding to the fault frequency information by a preset adjustment ratio; a signal-to-noise ratio acquisition module, which is used to obtain a signal-to-noise ratio index by performing logarithmic calculation on the signal interval energy and the difference obtained by subtracting the signal interval energy from the noise interval energy.

[0113] In a possible implementation of the present application, the analysis module includes: a second judgment module, which is used to determine whether the main bearing has a fault based on the total vibration parameters in the time domain type characteristics, and obtain a first judgment result; a third judgment module, which is used to determine whether the main bearing has a fault based on the target bandpass filter frequency band and the fault frequency amplitude in the spectrum type characteristics, and obtain a second judgment result; a fourth judgment module, which is used to determine whether the main bearing has a fault based on the impact period in the time domain impact type characteristics, and obtain a third judgment result; a fusion analysis module, which is used to perform fusion analysis on the first judgment result, the second judgment result and the third judgment result to obtain a fault judgment result of the main bearing.

[0114] In a possible implementation of the present application, the second judgment module includes: a rising trend calculation module, which is used to calculate the rising trend of the total vibration parameters in multiple periods to obtain multiple rising trend change rates, wherein the multiple periods include at least short-term, medium-term and long-term; a rising trend change rate judgment module, which is used to judge whether the multiple rising trend change rates are greater than multiple preset rising rate thresholds, wherein each period in the multiple periods corresponds to a different preset rising rate threshold; a first determination module, which is used to determine that the first judgment result is that there is a fault in the main bearing if the multiple rising trend change rates are greater than the multiple preset rising rate thresholds.

[0115] In a possible implementation of the present application, the third judgment module includes: a fault frequency acquisition module, which is used to obtain the fault frequency of the main bearing within a first preset time period based on the target bandpass filter frequency band and the fault frequency amplitude in the spectrum-like characteristics; a fault frequency judgment module, which is used to judge whether the fault frequency is greater than the preset fault frequency; and a second determination module, which is used to determine that the second judgment result is that there is a fault in the main bearing if the fault frequency is greater than the preset fault frequency.

[0116] In a possible implementation of the present application, the fourth judgment module includes: an impact amplitude trend acquisition module, which is used to respectively acquire a first impact amplitude trend of the impact amplitude corresponding to the impact cycle in a second preset time period, and a second impact amplitude trend of the impact amplitude corresponding to the impact cycle in a third preset time period, wherein the second preset time period is greater than the third preset time period; an upward trend change rate judgment module, which is used to judge whether the upward trend change rate of the first impact amplitude trend is greater than the first preset upward trend change rate, and whether the downward trend change rate of the second impact amplitude trend is less than the first preset downward trend change rate; a third determination module, which is used to determine that the third judgment result is that there is a fault in the main bearing if the upward trend change of the first impact amplitude trend is greater than the first preset upward trend change rate, and the downward trend change rate of the second impact amplitude trend is less than the first preset downward trend change rate.

[0117] In a possible implementation of the present application, the fusion analysis module includes: a target period judgment module, which is used to judge the target period of the main bearing fault based on the target bandpass filter frequency band in the spectrum type characteristics; a damage location judgment module, which is used to judge the specific damage location of the main bearing fault based on the fault frequency amplitude in the spectrum type characteristics and the impact period in the time domain impact type characteristics.

[0118] Exemplary Electronic Devices

[0119] As a third aspect of the present application, the present application further provides an electronic device, which stores computer program information. When the computer program information is executed by a processor, the processor executes any one of the main bearing fault warning methods mentioned above.

[0120] Figure 5 Shown is a device block diagram of an electronic device provided in one embodiment of the present application.

[0121] like Figure 5 As shown, the electronic device includes one or more processors 51 and a memory 52 .

[0122] The processor 51 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0123] The memory 52 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may run the program instructions to implement the main bearing fault warning method of each embodiment of the present application described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage medium.

[0124] In one example, the electronic device may further include: an input device 53 and an output device 54, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0125] When the electronic device is a stand-alone device, the input device 53 may be a communication network connector for receiving collected input signals from the first device and the second device.

[0126] In addition, the input device 53 may also include, for example, a keyboard, a mouse, etc.

[0127] The output device 54 can output various information to the outside, including the determined distance information, direction information, etc. The output device 54 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and the like.

[0128] Of course, to simplify, Figure 5 Only some of the components in the electronic device related to the present application are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device may further include any other appropriate components according to specific application conditions.

[0129] Exemplary computer-readable storage media

[0130] As a fourth aspect of the present application, the present application provides a computer-readable storage medium, the storage medium storing a computer program, the computer program being used to perform the following steps:

[0131] S1, obtaining fault diagnosis parameters of the main bearing, wherein the fault diagnosis parameters at least include a vibration signal, a rotation speed and fault frequency information of the main bearing;

[0132] S2, extracting features from the fault diagnosis parameters to obtain a multi-feature extraction result, wherein the multi-feature extraction result at least includes a time domain feature, a spectrum feature, and a time domain impact feature;

[0133] S3, performing fusion analysis on the multi-feature extraction results to obtain the fault judgment result of the main bearing.

[0134] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program information, which, when executed by a processor, enables the processor to execute the steps of the main bearing fault warning method according to various embodiments of the present application described in this specification.

[0135] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0136] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program information is stored. When the computer program information is executed by a processor, the processor executes the steps of the main bearing fault warning method according to various embodiments of the present application described in this specification.

[0137] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0138] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0139] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0140] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

Claims

1. A main bearing fault early warning method, characterized in that: include: Acquiring fault diagnosis parameters of the main bearing, wherein the fault diagnosis parameters at least include a vibration signal, a rotation speed, and fault frequency information of the main bearing; Performing feature extraction on the fault diagnosis parameters to obtain a multi-feature extraction result, wherein the multi-feature extraction result at least includes time domain features, spectrum features, and time domain impact features; The multi-feature extraction results are fused and analyzed to obtain a fault determination result of the main bearing.

2. The main bearing fault warning method according to claim 1, characterized in that: Perform feature extraction on the fault diagnosis parameters to obtain multiple feature extraction results, including: Preprocessing the fault diagnosis parameters to obtain an envelope spectrum of the main bearing, wherein the envelope spectrum is used to characterize a spectrum analysis result of an envelope of a vibration signal of the main bearing; The envelope spectrum is optimized and calculated based on a preset band-pass filter frequency band to obtain a target band-pass filter frequency band, wherein the target band-pass filter frequency band is used to characterize a frequency band corresponding to an identifiable fault frequency in the preset band-pass filter frequency band; Calculating the target bandpass filter frequency band to obtain the fault frequency amplitude corresponding to the main bearing; The frequency spectrum characteristics of the main bearing fault are determined based on the fault frequency amplitude.

3. The main bearing fault warning method according to claim 2, characterized in that: The envelope spectrum is optimized and calculated based on a preset bandpass filter frequency band to obtain a target bandpass filter frequency band, including: Performing traversal calculation on the envelope spectrum within the preset bandpass filter frequency band to obtain multiple groups of noise-signal interval indicators, wherein each group of noise-signal interval indicators includes a kurtosis indicator and a signal-to-noise ratio indicator; Determine whether there is a kurtosis index greater than a preset kurtosis parameter and a signal-to-noise ratio index greater than a preset signal-to-noise ratio parameter among multiple groups of noise-signal interval indicators; If there is a kurtosis index greater than a preset kurtosis parameter in the multiple groups of noise-signal interval indicators, and the signal-to-noise ratio index is greater than a preset signal-to-noise ratio parameter, obtaining a corresponding target noise-signal interval index; The bandpass filter frequency band corresponding to the target noise-signal interval indicator is determined as the target bandpass filter frequency band.

4. The main bearing fault warning method according to claim 3, characterized in that: The envelope spectrum within the preset bandpass filter frequency band is traversed and calculated to obtain multiple groups of noise-signal interval indicators, including: Acquiring a preset fluctuation amplitude of the vibration signal, wherein the preset fluctuation amplitude is determined by a sampling frequency of the vibration signal; By calculating the fault frequency information of the main bearing and the preset fluctuation amplitude, noise interval energy is obtained, and the noise interval energy is determined as the kurtosis index; Acquiring a signal interval energy of the main bearing, wherein the signal interval energy is greater than a product obtained by multiplying an amplitude corresponding to the fault frequency information by a preset adjustment ratio; The signal-to-noise ratio index is obtained by performing logarithmic calculation on the signal interval energy and the difference between the noise interval energy and the signal interval energy.

5. The main bearing fault warning method according to claim 1, characterized in that: The multi-feature extraction results are fused and analyzed to obtain the fault determination result of the main bearing, including: Based on the total vibration parameters in the time domain characteristics, determine whether the main bearing has a fault, and obtain a first determination result; Based on the target bandpass filter frequency band and the fault frequency amplitude in the spectrum characteristics, determining whether the main bearing has a fault, and obtaining a second determination result; Based on the impact cycle in the time domain impact characteristics, determine whether the main bearing has a fault, and obtain a third determination result; The first determination result, the second determination result and the third determination result are fused and analyzed to obtain a fault determination result of the main bearing.

6. The main bearing fault warning method according to claim 5, characterized in that: Based on the total vibration parameters in the time domain characteristics, it is determined whether the main bearing has a fault, and a first determination result is obtained, including: Calculating the rising trend of the total vibration parameter in multiple periods to obtain multiple rising trend change rates, wherein the multiple periods include at least short-term, medium-term and long-term; Determining whether the multiple rising trend change rates are greater than multiple preset rising rate thresholds, wherein each of the multiple periods corresponds to a different preset rising rate threshold; If the multiple rising trend change rates are greater than multiple preset rising rate thresholds, it is determined that the first determination result is that a main bearing fault exists.

7. The main bearing fault warning method according to claim 5, characterized in that: Based on the target bandpass filter frequency band and the fault frequency amplitude in the spectrum characteristics, it is determined whether the main bearing has a fault, and a second determination result is obtained, including: Based on the target bandpass filter frequency band and the fault frequency amplitude in the spectrum characteristics, the fault frequency of the main bearing in the first preset time period is obtained; Determining whether the fault frequency is greater than a preset fault frequency; If the fault frequency is greater than the preset fault frequency, it is determined that the second determination result is that there is a fault in the main bearing.

8. The main bearing fault warning method according to claim 5, characterized in that: Based on the impact cycle in the time domain impact characteristics, it is determined whether the main bearing has a fault, and a third determination result is obtained, including: Respectively obtaining a first impact amplitude trend of the impact amplitude corresponding to the impact cycle in a second preset time period, and a second impact amplitude trend of the impact amplitude corresponding to the impact cycle in a third preset time period, wherein the second preset time period is greater than the third preset time period; Determine whether the rising trend change rate of the first impact amplitude trend is greater than a first preset rising trend change rate, and whether the falling trend change rate of the second impact amplitude trend is less than the first preset falling trend change rate; If the rising trend change of the first impact amplitude trend is greater than the first preset rising trend change rate, and the falling trend change rate of the second impact amplitude trend is less than the first preset falling trend change rate, it is determined that the third judgment result is that the main bearing is faulty.

9. The main bearing fault warning method according to claim 5, characterized in that: The first determination result, the second determination result and the third determination result are fused and analyzed to obtain a fault determination result of the main bearing, including: Based on the target bandpass filter frequency band in the spectrum-like feature, determining the target period during which the main bearing has a fault; Based on the fault frequency amplitude in the frequency spectrum characteristics and the impact period in the time domain impact characteristics, the specific damaged part of the main bearing fault is determined.

10. An electronic device, characterized in that: The electronic device stores computer program information, and when the computer program information is executed by the processor, the processor executes the main bearing fault warning method according to any one of claims 1 to 9.

Images