Shaft crack fault identification method and device, equipment and medium
The method improves gear shaft crack detection by preprocessing vibration data to extract multi-dimensional features, addressing the limitations of existing methods and reducing complexity and cost.
Patent Information
- Application Number
- CN202510521905.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-24
- Publication Date
- 2025-07-15
AI Technical Summary
The prior art has problems of high difficulty and high cost when identifying axial crack failures. Ultrasonic detection requires coupling agent to operate in complex contact surfaces, machine vision detection is easily disturbed and difficult to detect internal failures, eddy current detection cannot detect deep failures, machine learning-based methods require a large amount of labeled data and low model interpretability.
By collecting the original vibration impact data, pre-processing is performed to obtain the impact characteristic values of the driving gear, semi-meshing spectrum, meshing spectrum and two-solar spectrum. These characteristic values are used to generate multi-dimensional fault characteristic values, and axial crack fault identification is combined with preset conditions to generate fault results.
It realizes more reliable and accurate shaft crack fault identification, reduces the difficulty and cost of identification, and is less difficult to extract fault characteristic values, can be early warning and diagnosed in advance, supports full-cycle monitoring, and reduces the risk of accidents.
Smart Images
Figure CN120316446A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of immune maintenance design, and particularly relates to a method, device, equipment and medium for identifying shaft crack faults. Background Art
[0002] Faults such as cracks and breaks in the gear drive shafts of transportation vehicles often occur, and when the faults are serious, such as after breaking, important accidents such as clearing passengers to the lower limit and locomotive breakdowns will occur. Therefore, the rail transit operation department hopes to carry out full-cycle monitoring of such faults for risk prevention.
[0003] At present, shaft crack fault identification can be carried out through ultrasonic testing. However, ultrasonic testing requires a coupling agent to contact the surface, the operation is complex, and it overly relies on professionals. The method of machine vision detection is easily interfered with and it is difficult to detect internal faults. Eddy current detection cannot detect deep faults. The intelligent diagnosis method based on machine learning requires a large amount of labeled data and the model interpretability is relatively low.
[0004] In summary, how to reduce the difficulty and cost of shaft crack fault identification is an issue to be solved in this field. Summary of the Invention
[0005] In view of this, the purpose of the present invention is to provide a method, device, equipment and medium for identifying shaft crack faults, which reduces the difficulty and cost of shaft crack fault identification. The specific solutions are as follows:
[0006] In the first aspect, the present application discloses a method for identifying shaft crack faults, including:
[0007] Collect the original vibration shock data of the component to be tested within a preset time period;
[0008] Preprocess the original vibration shock data to obtain various shock characteristic values of each single sample within the preset time period; wherein, each type of shock characteristic value includes the active gear shock characteristic intensity value, the bispectrum shock characteristic intensity value, the semi-meshing spectrum shock characteristic intensity value, and the meshing spectrum shock characteristic intensity value;
[0009] Obtain multi-dimensional fault characteristic values according to each type of shock characteristic value;
[0010] Identify the shaft crack fault of the main shaft according to the fault characteristic values to generate the fault result of the main shaft.
[0011] Optionally, the obtaining multi-dimensional fault characteristic values according to each type of shock characteristic value includes:
[0012] Mark the samples with the active gear shock characteristic intensity value greater than the first preset intensity threshold to obtain the first marked samples;
[0013] Mark the samples whose impact characteristic intensity values of the two-arc spectrum are greater than the first preset intensity threshold to obtain the second marked samples, mark the samples whose impact characteristic intensity values of the meshing spectrum are greater than the first preset intensity threshold to obtain the third marked samples, and mark the samples whose impact characteristic intensity values of the semi-meshing spectrum are greater than the first preset intensity threshold to obtain the fourth marked samples;
[0014] Determine the average value of the impact characteristic intensity values of the semi-meshing spectrum of the fourth marked samples;
[0015] Respectively determine the number of the first marked samples, the number of the second marked samples, the number of the third marked samples, and the average value of the impact characteristic intensity values of the semi-meshing spectrum as the first fault characteristic value, the second fault characteristic value, the third fault characteristic value, and the fourth fault characteristic value.
[0016] Optionally, the shaft crack fault identification method further includes:
[0017] If the driving shaft meets the first preset shaft crack symptom condition, generate a first fault result; wherein, the first preset shaft crack symptom condition is that the rotational speed of the impact characteristic intensity value of the semi-meshing spectrum and the impact characteristic intensity value in the fourth marked samples both decrease as the operation time goes by.
[0018] Optionally, the step of identifying the shaft crack fault of the driving shaft according to the fault characteristic values to generate the fault result of the driving shaft includes:
[0019] If the driving shaft does not meet the first preset shaft crack symptom condition, then judge whether the driving shaft meets the second preset shaft crack symptom condition based on the first fault characteristic value, the second fault characteristic value, the third fault characteristic value, and the fourth fault characteristic value; wherein, the second preset shaft crack symptom condition is that the fourth fault characteristic value is greater than the second preset intensity threshold and the first fault characteristic value, the second fault characteristic value, and the third fault characteristic value are all greater than the first preset quantity threshold;
[0020] If it is determined that the driving shaft meets the second preset shaft crack symptom condition, generate a first fault result to perform fault warning based on the first fault result.
[0021] Optionally, the first fault result indicates that the driving shaft has a shaft crack symptom caused by shaft fatigue.
[0022] Optionally, the step of identifying the shaft crack fault of the driving shaft according to the fault characteristic values to generate the fault result of the driving shaft includes:
[0023] If the driving shaft meets the first preset shaft crack symptom condition and the second preset shaft crack symptom condition, it is determined that the driving shaft meets the first preset shaft crack fault diagnosis condition, and a second fault result is generated;
[0024] Among them, the first preset shaft crack symptom condition is that the rotational speed at which the semi-meshing spectrum impact characteristic intensity value appears in the fourth marked sample and the semi-meshing spectrum impact characteristic intensity value both decrease over time; the second preset shaft crack symptom condition is that the fourth fault characteristic value is greater than the second preset intensity threshold, and the first fault characteristic value, the second fault characteristic value, and the third fault characteristic value are all greater than the first preset quantity threshold.
[0025] Optionally, the obtaining of multi-dimensional fault characteristic values according to various types of the impact characteristic values further includes:
[0026] Screen out double marked samples from the second marked sample and the third marked sample where the impact characteristic intensity value of the double-sided solitary spectrum signal is greater than the third preset intensity threshold and the impact characteristic intensity value of the meshing spectrum signal is greater than the fourth preset intensity threshold, and determine the quantity of the double marked samples as the fifth fault characteristic value.
[0027] Optionally, the identifying of the shaft crack fault of the driving shaft according to the fault characteristic values to generate the fault result of the driving shaft includes:
[0028] If the fifth fault characteristic value is greater than the second preset quantity threshold, it is determined that the driving shaft meets the second preset shaft crack fault diagnosis condition, and a second fault result is generated for fault alarm based on the second fault result.
[0029] Optionally, the second fault result indicates that the driving shaft has a shaft crack fault and the cause of the shaft crack fault is stress concentration at the variable-diameter transition circle between the bearing of the driving shaft and the driving gear; among them, the reason for the stress concentration at the variable-diameter transition circle is that the driving shaft is subjected to a radial thrust from the driving gear.
[0030] Optionally, the preprocessing of the original vibration impact data to obtain various types of impact characteristic values of each single sample within the preset time period includes:
[0031] Perform sampling processing on the original impact data to convert the continuous-time signal into a discrete-time signal;
[0032] Perform Fourier transform on the discrete-time signal to convert the discrete-time signal from the time domain to the frequency domain, obtain the initial frequency domain signal, and extract the spectral information of the initial frequency domain signal.
[0033] Filter the initial frequency-domain signal to remove the noise signal and obtain the filtered frequency-domain signal;
[0034] Normalize the filtered frequency-domain signal to eliminate the dimension difference and obtain the normalized frequency-domain signal;
[0035] Extract features from the normalized frequency-domain signal to obtain the impact feature values of each single sample.
[0036] In a second aspect, the present application discloses a shaft crack fault identification device, including:
[0037] A data acquisition module for acquiring the original vibration impact data of the component to be measured within a preset time period;
[0038] A preprocessing module for preprocessing the original vibration impact data to obtain various impact feature values of each single sample within the preset time period; wherein, the various impact feature values include the impact feature intensity value of the driving gear, the impact feature intensity value of the bispectrum, the impact feature intensity value of the half-engagement spectrum, and the impact feature intensity value of the engagement spectrum;
[0039] A fault feature value acquisition module for acquiring multi-dimensional fault feature values according to the various impact feature values;
[0040] A fault identification module for identifying the shaft crack fault of the main shaft according to the fault feature values to generate the fault result of the main shaft.
[0041] In a third aspect, the present application discloses an electronic device, including:
[0042] A memory for storing a computer program;
[0043] A processor for executing the computer program to implement the steps of the shaft crack fault identification method disclosed above.
[0044] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, the computer program, when executed by a processor, implements the steps of the shaft crack fault identification method disclosed above.
[0045] The beneficial effects of this application are as follows: This application collects the original vibration and shock data of the component to be measured within a preset time period; preprocesses the original vibration and shock data to obtain various shock characteristic values of each single sample within the preset time period; among them, each type of shock characteristic value includes the active gear shock characteristic intensity value, the double-sided spectral shock characteristic intensity value, the half-meshing spectral shock characteristic intensity value, and the meshing spectral shock characteristic intensity value; obtains multi-dimensional fault characteristic values according to each type of shock characteristic value; identifies the shaft crack fault of the active shaft according to the fault characteristic values to generate the fault result of the active shaft. It can be seen that after preprocessing the original vibration and shock data of the component to be measured within a preset time period, this application obtains various shock characteristic values of each single sample within the preset time period, that is, obtains the active gear shock characteristic intensity value, the double-sided spectral shock characteristic intensity value, the half-meshing spectral shock characteristic intensity value, and the meshing spectral shock characteristic intensity value; further, this application obtains multi-dimensional fault characteristic values according to the active gear shock characteristic intensity value, the double-sided spectral shock characteristic intensity value, the half-meshing spectral shock characteristic intensity value, and the meshing spectral shock characteristic intensity value, where the double-sided spectrum is a prominent isolated spectrum that is twice the characteristic spectrum of the active gear generated due to the shaft crack fault during the gear meshing process, the meshing spectrum is the meshing frequency spectral line during the rotation of the active gear, and the half-meshing spectrum is half of the meshing spectrum, that is to say, this application starts from the shaft crack fault mechanism and extracts fault characteristic values from multiple dimensions. In this way, the shaft crack fault of the active shaft is identified according to the fault characteristic values in multiple dimensions, and the generated fault result of the active shaft is more reliable and accurate, and the difficulty of extracting fault characteristic values is small, thereby reducing the difficulty and cost of shaft crack fault identification. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.
[0047] Figure 1 It is a flowchart of a shaft crack fault identification method disclosed in this application;
[0048] Figure 2 It is a schematic diagram of a specific vehicle-mounted system architecture disclosed in this application;
[0049] Figure 3 It is a schematic diagram of a specific shaft crack fault identification disclosed in this application;
[0050] Figure 4 It is a schematic diagram of the structure of a shaft crack fault identification device disclosed in this application;
[0051] Figure 5 A structural diagram of an electronic device disclosed in this application. Specific embodiments
[0052] The following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
[0053] Faults such as cracks and breaks in the gear drive shaft of transportation vehicles occur frequently. When the faults are serious, such as breaks, important accidents such as passenger evacuation limits and locomotive breakdowns will occur. Therefore, the rail transit operation department hopes to carry out full-cycle monitoring of such faults for risk prevention.
[0054] Currently, the identification of drive shaft crack faults can be achieved through ultrasonic testing. However, ultrasonic testing requires a coupling agent to contact the surface, with complex operations and over-reliance on professionals. The method of machine vision detection is easily interfered with and difficult to detect internal faults. Eddy current testing cannot detect deep faults. The intelligent diagnosis method based on machine learning requires a large amount of labeled data, and the model interpretability is relatively low.
[0055] Therefore, this application correspondingly provides a shaft crack fault identification solution to reduce the difficulty and cost of shaft crack fault identification.
[0056] See Figure 1 As shown, an embodiment of this application discloses a shaft crack fault identification method, including:
[0057] Step S11: Collect the original vibration shock data of the component to be tested within a preset time period.
[0058] For example Figure 2 As shown in a specific schematic diagram of an on-vehicle system architecture, based on the generalized resonance fault diagnosis technology, during the operation of the vehicle, the status of the diagnostic component is monitored in real time through the on-vehicle system. For example, the drive shaft of the vehicle can be monitored through a diagnostic instrument, a pre-processor, and a composite sensor at each sampling time within a preset time period. In the rotational speed tracking sampling method, data samples are collected every day within the past 3 months. When the wheelset of the vehicle rotates one circle, N points are collected, where N is a fixed value.
[0059] Step S12: Preprocess the original vibration shock data to obtain various shock characteristic values of each single sample within the preset time period; among them, each type of shock characteristic value includes the active gear shock characteristic intensity value, the bispectrum shock characteristic intensity value, the semi-meshing spectrum shock characteristic intensity value, and the meshing spectrum shock characteristic intensity value.
[0060] In this embodiment, preprocessing the original vibration and shock data to obtain various shock characteristic values of each single sample within the preset time period includes: sampling the original shock data to convert a continuous-time signal into a discrete-time signal; performing a Fourier transform on the discrete-time signal to convert the discrete-time signal from the time domain to the frequency domain, obtaining an initial frequency-domain signal, and extracting the spectral information of the initial frequency-domain signal; performing a filtering process on the initial frequency-domain signal to remove noise signals, obtaining a filtered frequency-domain signal; performing a normalization process on the filtered frequency-domain signal to eliminate the dimension difference, obtaining a normalized frequency-domain signal; and performing feature extraction on the normalized frequency-domain signal to obtain the shock characteristic values of each single sample.
[0061] It can be understood that the collected original vibration and shock data is continuous time-domain data. In order to obtain the shock characteristic values, it is necessary to convert the time-domain data into frequency-domain data. Specifically, first, convert the continuous-time signal into a discrete-time signal, that is, sample the original shock data, and perform a Fourier transform (fast Fourier transform, i.e., FFT) on the discrete-time signal to convert the discrete-time signal from the time domain to the frequency domain, obtaining an initial frequency-domain signal. Since there may be noise signals in the collected original vibration and shock data due to signal fluctuations and surrounding signal interference, noise elimination is also required. Therefore, perform a filtering process on the initial frequency-domain signal to remove noise signals, obtaining a filtered frequency-domain signal. Further, there is a dimension difference between different types of signals, and it is necessary to perform a normalization process on the filtered frequency-domain signal to eliminate the dimension difference, obtaining a normalized frequency-domain signal. Perform feature extraction on the normalized frequency-domain signal to obtain the shock characteristic values of each single sample, that is, the active gear shock characteristic intensity value zdcl_db, the double isolated spectrum shock characteristic intensity value egp_db, the half-meshing spectrum shock characteristic intensity value bnp_db, and the meshing spectrum shock characteristic intensity value nhp_db of each single sample. Among them, the double isolated spectrum refers to the prominent isolated spectrum that is twice the characteristic spectrum of the gear on this shaft generated due to shaft crack faults during gear meshing. The meshing spectrum refers to the meshing frequency spectral line during the rotation of the gear on this shaft. In this embodiment, the meshing spectrum spectral number is specifically 10.24 * the number of large gears. The half-meshing spectrum is half of the meshing spectrum.
[0062] The double isolated spectrum specifically refers to: through the analysis of the resonance demodulation wave obtained by the resonance demodulation separation processing of the vibration impact signal monitored on the bearing near the gear and the sampling by the AD (Analog-to-digital) converter, if it is found that there are 2 clusters of meshing shock waves that are basically symmetric in each rotation period of the axis where the gear is located in the resonance demodulation time domain waveform, and there is a meshing impact spectrum of the gear in the FFT analysis spectrum of the resonance demodulation time domain waveform, and there is an isolated spectrum that is 2 times the characteristic frequency equal to the rotational speed frequency of the gear axis, that is, the double isolated spectrum.
[0063] The semi-meshing spectrum specifically refers to: when the meshing frequency F = FDN × ZX is equal to 2 times the generalized resonance frequency FG of the shafting, there are clear spectral lines with the largest amplitude, having both the meshing impact spectrum F and the generalized resonance spectrum FG (Frequency Generator), and FG = F / 2, which is the semi-meshing spectrum.
[0064] Step S13: Obtain multi-dimensional fault characteristic values according to various types of the impact characteristic values.
[0065] In this embodiment, obtaining multi-dimensional fault characteristic values according to various types of the impact characteristic values includes: marking the samples with the impact characteristic intensity value of the driving gear greater than the first preset intensity threshold to obtain the first marked samples; marking the samples with the impact characteristic intensity value of the double isolated spectrum greater than the first preset intensity threshold to obtain the second marked samples, marking the samples with the impact characteristic intensity value of the meshing spectrum greater than the first preset intensity threshold to obtain the third marked samples, marking the samples with the impact characteristic intensity value of the semi-meshing spectrum greater than the first preset intensity threshold to obtain the fourth marked samples; determining the mean value of the semi-meshing spectrum impact characteristic intensity value of the fourth marked samples; taking the number of the first marked samples, the number of the second marked samples, the number of the third marked samples, and the mean value of the semi-meshing spectrum impact characteristic intensity value as the first fault characteristic value, the second fault characteristic value, the third fault characteristic value, and the fourth fault characteristic value respectively.
[0066] Obtain the first fault characteristic value, the second fault characteristic value, the third fault characteristic value, and the fourth fault characteristic value according to the impact characteristic intensity value of the driving gear, the impact characteristic intensity value of the double isolated spectrum, the impact characteristic intensity value of the semi-meshing spectrum, and the impact characteristic intensity value of the meshing spectrum respectively. First, mark the samples with the impact characteristic intensity value of the driving gear, the impact characteristic intensity value of the double isolated spectrum, the impact characteristic intensity value of the semi-meshing spectrum, and the impact characteristic intensity value of the meshing spectrum. The specific process is as follows:
[0067] 1) Mark the samples with the impact characteristic intensity value of the driving gear greater than the first preset intensity threshold to obtain the first marked samples;
[0068] 2) Mark the samples whose impact characteristic intensity values of the double-side meshing spectrum are greater than the first preset intensity threshold to obtain the second marked samples;
[0069] 3) Mark the samples whose impact characteristic intensity values of the meshing spectrum are greater than the first preset intensity threshold to obtain the third marked samples;
[0070] 4) Mark the samples whose impact characteristic intensity values of the semi-meshing spectrum are greater than the first preset intensity threshold to obtain the fourth marked samples, and determine the average value of the impact characteristic intensity values of the semi-meshing spectrum of the fourth marked samples;
[0071] Among them, the first preset intensity threshold is 0, that is to say, each marked sample is the sample whose corresponding impact characteristic value is greater than 0. In this way, the number of the first marked samples, the number of the second marked samples, the number of the third marked samples, and the average value of the impact characteristic intensity values of the semi-meshing spectrum are respectively determined as the first fault characteristic value, the second fault characteristic value, the third fault characteristic value, and the fourth fault characteristic value.
[0072] Further, obtaining multi-dimensional fault characteristic values according to the various impact characteristic values further includes: screening out double-marked samples from the second marked samples and the third marked samples, where the impact characteristic intensity value of the double-side meshing spectrum signal of the double-marked samples is greater than the third preset intensity threshold and the impact characteristic intensity value of the meshing spectrum signal is greater than the fourth preset intensity threshold, and determining the number of the double-marked samples as the fifth fault characteristic value.
[0073] After obtaining the second marked samples and the third marked samples, it is necessary to screen out double-marked samples from the second marked samples and the third marked samples. The double-marked samples refer to the samples whose impact characteristic intensity value of the double-side meshing spectrum signal is greater than the third preset intensity threshold a and the impact characteristic intensity value of the meshing spectrum signal is greater than the fourth preset intensity threshold b. First, intersection marked samples can be screened out from the second marked samples and the third marked samples, that is, the intersection marked samples belong to both the second marked samples and the third marked samples. Then, first screening marked samples whose impact characteristic intensity value of the double-side meshing spectrum signal is greater than the third preset intensity threshold are screened out from the intersection marked samples. Then, second screening marked samples whose impact characteristic intensity value of the meshing spectrum signal is greater than the fourth preset intensity threshold are screened out from the first screening marked samples. The second screening marked samples are the double-marked samples, and the number of the double-marked samples is determined as the fifth fault characteristic value.
[0074] Step S14: Identify the shaft crack fault of the driving shaft according to the fault characteristic values to generate the fault result of the driving shaft.
[0075] In the first embodiment where there are signs of shaft crack in the driving shaft, it further includes: if the driving shaft meets the first preset shaft crack sign condition, generating a first fault result; wherein, the first preset shaft crack sign condition is that the rotational speed at which the semi-meshing spectrum impact characteristic intensity value appears in the fourth marked sample and the semi-meshing spectrum impact characteristic intensity value both decrease as the running time goes by.
[0076] Since the rotational speed can also reflect the shaft crack fault of the driving shaft, it is also necessary to collect the rotational speed at which the semi-meshing spectrum impact characteristic intensity value appears. And if the driving shaft meets the first preset shaft crack sign condition, that is, the rotational speed at which the semi-meshing spectrum impact characteristic intensity value appears in the fourth marked sample and the semi-meshing spectrum impact characteristic intensity value both decrease as the running time goes by, it indicates that there are signs of shaft crack in the driving shaft.
[0077] In the second embodiment where there are signs of shaft crack in the driving shaft, the identifying the shaft crack fault of the driving shaft according to the fault characteristic values to generate the fault result of the driving shaft includes: if the driving shaft does not meet the first preset shaft crack sign condition, judging whether the driving shaft meets the second preset shaft crack sign condition based on the first fault characteristic value, the second fault characteristic value, the third fault characteristic value and the fourth fault characteristic value; wherein, the second preset shaft crack sign condition is that the fourth fault characteristic value is greater than a second preset intensity threshold and the first fault characteristic value, the second fault characteristic value and the third fault characteristic value are all greater than a first preset quantity threshold; if it is determined that the driving shaft meets the second preset shaft crack sign condition, generating a first fault result to perform fault warning based on the first fault result.
[0078] If the driving shaft does not meet the first preset shaft crack sign condition but meets the second preset shaft crack sign condition, it indicates that there are still signs of shaft crack in the driving shaft, that is, the driving shaft does not meet the first preset shaft crack sign condition but the fourth fault characteristic value is greater than the second preset intensity threshold and the first fault characteristic value, the second fault characteristic value and the third fault characteristic value are all greater than the first preset quantity threshold. That is to say, meeting the four conditions of 1) the mean value of the semi-meshing spectrum impact characteristic intensity value is greater than the second preset intensity threshold TQ, 2) the quantity of the first marked sample is greater than the first preset quantity threshold TP, 3) the quantity of the second marked sample is greater than the first preset quantity threshold TP, and 4) the quantity of the third marked sample is greater than the first preset quantity threshold TP indicates that the driving shaft meets the second preset shaft crack sign condition.
[0079] Further, if the driving shaft only meets the first preset shaft cracking symptom condition or the second preset shaft cracking symptom condition, it indicates that there is a shaft cracking symptom in the driving shaft, and then a first fault result is generated for fault warning based on the first fault result. It can be understood that when the driving shaft only meets the first preset shaft cracking symptom condition or the second preset shaft cracking symptom condition, it means that there is a shaft cracking symptom in the driving shaft but no shaft cracking fault has occurred yet, only shaft cracking characteristics exist. Therefore, only fault warning is required to pre-warn that there is a shaft cracking symptom in the driving shaft in time for maintenance of the driving shaft as soon as possible to avoid subsequent faults.
[0080] In this embodiment, the first fault result characterizes that there is a shaft cracking symptom in the driving shaft caused by shaft fatigue. The first fault result indicates that there is a shaft cracking symptom in the driving shaft caused by shaft fatigue. Maintenance personnel can closely monitor the driving shaft according to the first fault result to check for the shaft cracking symptom, try to eliminate the shaft cracking characteristics, and avoid developing into a shaft cracking fault later.
[0081] In the first embodiment where the driving shaft has a shaft cracking fault, the step of identifying the shaft cracking fault of the driving shaft according to the fault characteristic value to generate the fault result of the driving shaft includes: if the driving shaft meets the first preset shaft cracking symptom condition and the second preset shaft cracking symptom condition, it is determined that the driving shaft meets the first preset shaft cracking fault diagnosis condition, and a second fault result is generated; wherein, the first preset shaft cracking symptom condition is that the rotational speed at which the semi-engaged spectrum impact characteristic intensity value appears in the fourth marked sample and the semi-engaged spectrum impact characteristic intensity value both decrease over time; the second preset shaft cracking symptom condition is that the fourth fault characteristic value is greater than the second preset intensity threshold and the first fault characteristic value, the second fault characteristic value, and the third fault characteristic value are all greater than the first preset quantity threshold.
[0082] If the driving shaft meets both the first preset shaft cracking symptom condition and the second preset shaft cracking symptom condition, it indicates that there is a shaft cracking fault in the driving shaft, that is, it is determined that the driving shaft meets the first preset shaft cracking fault diagnosis condition, and a second fault result is generated. That is to say, not only does the rotational speed at which the semi-engaged spectrum impact characteristic intensity value appears in the fourth marked sample and the semi-engaged spectrum impact characteristic intensity value both decrease over time, but also the fourth fault characteristic value is greater than the second preset intensity threshold and the first fault characteristic value, the second fault characteristic value, and the third fault characteristic value are all greater than the first preset quantity threshold.
[0083] In an embodiment of the second type of active shaft having a shaft crack fault, the shaft crack fault is identified on the active shaft according to the fault characteristic value to generate a fault result of the active shaft, including: if the fifth fault characteristic value is greater than a second preset quantity threshold, it is determined that the active shaft meets the second preset shaft crack fault diagnosis condition, and a second fault result is generated to issue a fault alarm based on the second fault result.
[0084] Furthermore, if the fifth fault characteristic value is greater than the second preset quantity threshold, it is determined that the active shaft meets the second preset shaft crack fault diagnosis condition, that is, the number of double-marked samples is greater than the second preset quantity threshold 0, and a second fault result is generated to perform a fault alarm based on the second fault result.
[0085] It can be understood that if the first preset shaft crack fault diagnosis condition and / or the second preset shaft crack fault diagnosis condition are met, a second fault result is generated, that is, the active shaft currently has a shaft crack fault, and the situation is more serious than the existence of shaft crack signs, that is, it has developed into a fault, so it is necessary to issue a fault alarm based on the second fault result to inform the maintenance personnel of the current fault situation so that the maintenance personnel can repair the active shaft and eliminate the existing shaft crack fault.
[0086] In this embodiment, the second fault result indicates that the active shaft has a shaft crack fault and the cause of the shaft crack fault is that there is stress concentration at the variable diameter transition circle between the bearing of the active shaft and the active gear; wherein, the cause of the stress concentration at the variable diameter transition circle is that the active shaft is subjected to radial thrust from the active gear. The second fault result includes several parts, namely, fault signs and fault causes. Among them, the fault sign is that the active shaft has a shaft crack fault. The fault cause is that during the gear meshing process, the maximum radial force acting on the active shaft always occurs when the shaft rotates to mesh with the driven gear at a fixed position, and is not evenly or randomly distributed in all directions, thereby converting the persistent radial force into an alternating torque, resulting in a shaft crack fault. Therefore, maintenance personnel can also perform corresponding operations according to the cause of the fault to eliminate the shaft crack fault. The root cause of the second fault result is the mismatch between the parameters of the bearing of the active shaft and the driven gear or the mismatch between the bearing of the driven shaft and the active gear, which can further guide the parameter design improvement of the bearing and the gear.
[0087] It can be seen that after preprocessing the original vibration and shock data of the component to be measured within the preset time period in this application, various shock characteristic values of each single sample within the preset time period are obtained, that is, the shock characteristic intensity value of the driving gear, the shock characteristic intensity value of the double-sided spectrum, the shock characteristic intensity value of the half-meshing spectrum, and the shock characteristic intensity value of the meshing spectrum are obtained; further, this application obtains multi-dimensional fault characteristic values according to the shock characteristic intensity value of the driving gear, the shock characteristic intensity value of the double-sided spectrum, the shock characteristic intensity value of the half-meshing spectrum, and the shock characteristic intensity value of the meshing spectrum. Among them, the double-sided spectrum is a prominent isolated spectrum that is twice the characteristic spectrum of the driving gear due to the shaft crack fault during the gear meshing process, the meshing spectrum is the meshing frequency spectral line during the rotation of the driving gear, and the half-meshing spectrum is half of the meshing spectrum. That is to say, this application starts from the shaft crack fault mechanism and extracts fault characteristic values from multiple dimensions. The fault characteristic values include the number of the first marked samples, the number of the second marked samples, the number of the third marked samples, the mean value of the shock characteristic intensity value of the half-meshing spectrum, and the number of the double-marked samples. Then, according to these fault characteristic values satisfying different conditions, the fault result of the driving shaft is determined. That is, if the first preset shaft crack symptom condition or the second preset shaft crack symptom condition is satisfied, the first fault result indicating that there is a shaft crack symptom caused by shaft fatigue in the driving shaft is generated, that is, it indicates that the current driving shaft only has shaft crack symptoms or early signs. Therefore, a warning is issued based on the first fault result so that the maintenance personnel can closely monitor the shaft crack characteristics of the driving shaft before the fault occurs and try to avoid subsequent failures. If the first preset shaft crack fault diagnosis condition and / or the second preset shaft crack fault diagnosis condition are satisfied, it means that the driving shaft currently has a shaft crack fault, rather than just having shaft crack characteristics. Therefore, the second fault result including the shaft crack phenomenon and the shaft crack cause is generated. In this way, the maintenance personnel can repair the driving shaft according to the shaft crack phenomenon and the shaft crack cause to avoid more serious consequences caused by the shaft crack fault. It can be seen that this application performs fault identification from multi-dimensional fault characteristics and generates different fault results according to different conditions satisfied by the driving shaft, realizing a more comprehensive life cycle management of the driving shaft and enabling early prevention of fault occurrence; further, because the difficulty of extracting fault characteristic values is small, the difficulty and cost of shaft crack fault identification are reduced.
[0088] As Figure 3 shown in a specific shaft crack fault identification schematic diagram, a shaft crack fault diagnosis case of a certain type of locomotive is used to illustrate this application accordingly. The shaft crack fault identification process mainly includes data acquisition, shock characteristic value acquisition, fault characteristic acquisition, condition matching, and result generation parts. Among them, the specific process is as follows:
[0089] 1) In data acquisition, during the vehicle operation, the on-vehicle system is used to realize real-time monitoring of the state of the diagnostic component, and the original vibration and shock data of the component to be measured within the recent 3 months and the corresponding rotational speed data are collected in the rotational speed tracking sampling mode.
[0090] 2) In the impact eigenvalue acquisition part, first, preprocess the original vibration impact data, including sampling, Fourier transform, filtering, and normalization. Then, extract features from the normalized frequency-domain signal to obtain the impact eigenvalues of each single sample, namely, the impact characteristic intensity value of the driving gear, the impact characteristic intensity value of the bispectrum, the impact characteristic intensity value of the half-meshing spectrum, and the impact characteristic intensity value of the meshing spectrum.
[0091] 3) In the fault feature acquisition part, the obtained fault feature values are as follows:
[0092] 3.1) Mark the samples whose impact characteristic intensity value of the driving gear is greater than the first preset intensity threshold to obtain the first marked samples, and determine the number of the first marked samples as the first fault feature value;
[0093] 3.2) Mark the samples whose impact characteristic intensity value of the bispectrum is greater than the first preset intensity threshold to obtain the second marked samples, and determine the number of the second marked samples as the second fault feature value;
[0094] 3.3) Mark the samples whose impact characteristic intensity value of the meshing spectrum is greater than the first preset intensity threshold to obtain the third marked samples, and determine the number of the third marked samples as the third fault feature value;
[0095] 3.4) Determine the mean value of the impact characteristic intensity value of the half-meshing spectrum of the fourth marked samples, and determine the mean value of the impact characteristic intensity value of the half-meshing spectrum as the fourth fault feature value;
[0096] 3.5) Mark the samples whose impact characteristic intensity value of the half-meshing spectrum is greater than the first preset intensity threshold to obtain the fourth marked samples. Then, screen out the double-marked samples from the third marked samples and the fourth marked samples whose impact characteristic intensity value of the bispectrum signal is greater than the third preset intensity threshold and the impact characteristic intensity value of the meshing spectrum signal is greater than the fourth preset intensity threshold, and determine the number of the double-marked samples as the fifth fault feature value.
[0097] 4) The condition matching part is the logical judgment part, specifically:
[0098] 4.1) Judge whether the drive shaft meets the first preset shaft crack symptom condition, that is, whether there is a rotational speed of the impact characteristic intensity value of the half-meshing spectrum in the fourth marked samples and whether the impact characteristic intensity value of the half-meshing spectrum decreases with the passage of the running time. If so, it is determined that the drive shaft meets the first preset shaft crack symptom condition;
[0099] 4.2) If the first preset shaft cracking symptom condition is not satisfied, then determine whether the second preset shaft cracking symptom condition is satisfied, that is, determine whether the fourth fault characteristic value is greater than the second preset intensity threshold TQ and the first, second, and third fault characteristic values are all greater than the first preset quantity threshold TP. If so, the second preset shaft cracking symptom condition is satisfied;
[0100] 4.3) If the driving shaft satisfies both the first preset shaft cracking symptom condition and the second preset shaft cracking symptom condition, then it is determined that the drive shaft satisfies the first preset shaft cracking fault diagnosis condition;
[0101] 4.4) If the fifth fault characteristic value is greater than the second preset quantity threshold 0, then it is determined that the driving shaft satisfies the second preset shaft cracking fault diagnosis condition.
[0102] 5) After determining that the driving shaft satisfies the corresponding condition, the corresponding fault result is generated. Specifically:
[0103] 5.1) If the driving shaft satisfies the first preset shaft cracking symptom condition or the second preset shaft cracking symptom condition, then the first fault result is generated, that is, it indicates that the driving shaft currently only has shaft cracking characteristics but no shaft cracking fault, so as to perform fault warning based on the first fault result;
[0104] 5.2) If the driving shaft satisfies the first preset shaft cracking fault diagnosis condition and / or the second preset shaft cracking fault diagnosis condition, then the second fault result is generated, that is, the driving shaft currently has a shaft cracking fault, the situation is relatively serious, and an alarm is made based on the second fault result; wherein, the second fault result indicates that the driving shaft has a shaft cracking fault and the reason for the shaft cracking fault is that the driving shaft is subjected to a radial thrust from the driving gear, resulting in stress concentration at the variable diameter transition circle between the bearing of the driving shaft and the driving gear.
[0105] See Figure 4 As shown in
[0106] A data acquisition module 11, configured to acquire the original vibration and shock data of the component to be measured within a preset time period;
[0107] A preprocessing module 12, configured to preprocess the original vibration and shock data to obtain various shock characteristic values of each single sample within the preset time period; wherein, each of the various shock characteristic values includes the shock characteristic intensity value of the driving gear, the shock characteristic intensity value of the double-sided spectrum, the shock characteristic intensity value of the half-engaged spectrum, and the shock characteristic intensity value of the engaged spectrum;
[0108] A fault characteristic value acquisition module 13, configured to acquire multi-dimensional fault characteristic values according to the various shock characteristic values;
[0109] A fault identification module 14 is configured to identify a shaft crack fault of the driving shaft according to the fault characteristic values, so as to generate a fault result of the driving shaft.
[0110] The beneficial effects of the present application are as follows: The present application collects the original vibration and impact data of the component to be measured within a preset time period; preprocesses the original vibration and impact data to obtain various impact characteristic values of each single sample within the preset time period; wherein, each of the various impact characteristic values includes the impact characteristic intensity value of the driving gear, the impact characteristic intensity value of the bispectrum, the impact characteristic intensity value of the half-meshing spectrum, and the impact characteristic intensity value of the meshing spectrum; obtains multi-dimensional fault characteristic values according to each of the various impact characteristic values; identifies a shaft crack fault of the driving shaft according to the fault characteristic values, so as to generate a fault result of the driving shaft. It can be seen that after preprocessing the original vibration and impact data of the component to be measured within a preset time period, the present application obtains various impact characteristic values of each single sample within the preset time period, that is, obtains the impact characteristic intensity value of the driving gear, the impact characteristic intensity value of the bispectrum, the impact characteristic intensity value of the half-meshing spectrum, and the impact characteristic intensity value of the meshing spectrum; further, the present application obtains multi-dimensional fault characteristic values according to the impact characteristic intensity value of the driving gear, the impact characteristic intensity value of the bispectrum, the impact characteristic intensity value of the half-meshing spectrum, and the impact characteristic intensity value of the meshing spectrum, wherein the bispectrum is a prominent isolated spectrum that is twice the characteristic spectrum of the driving gear generated due to a shaft crack fault during the gear meshing process, the meshing spectrum is the meshing frequency spectral line during the rotation of the driving gear, and the half-meshing spectrum is half of the meshing spectrum, that is to say, the present application starts from the shaft crack fault mechanism and extracts fault characteristic values from multiple dimensions. In this way, identifying a shaft crack fault of the driving shaft according to the fault characteristic values in multiple dimensions, the generated fault result of the driving shaft is more reliable and accurate, and the difficulty of extracting fault characteristic values is small, thereby reducing the difficulty and cost of shaft crack fault identification.
[0111] Further, an embodiment of the present application also provides an electronic device. Figure 5 It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment, and the content in the figure should not be considered as any limitation on the scope of use of the present application.
[0112] Figure 5 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Specifically, it may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the shaft crack fault identification method executed by the electronic device disclosed in any of the foregoing embodiments.
[0113] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device; the communication interface 24 can create a data transmission channel between the electronic device and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and no specific limitation is imposed here; the input / output interface 25 is used to obtain external input data or output data to the outside, and the specific interface type can be selected according to specific application needs, and no specific limitation is imposed here.
[0114] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one of the following hardware forms: DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor used to process data in the wake state, also known as the CPU (Central Processing Unit); the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may be integrated with a GPU (Graphics Processing Unit), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may further include an AI (Artificial Intelligence) processor, and the AI processor is used to process computing operations related to machine learning.
[0115] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, a random access memory, a magnetic disk, or an optical disc, etc. The resources stored thereon include an operating system 221, a computer program 222, and data 223, etc., and the storage method can be temporary storage or permanent storage.
[0116] Among them, the operating system 221 is used to manage and control each hardware device and the computer program 222 on the electronic device, so as to implement the operation and processing of the massive data 223 in the memory 22 by the processor 21. It can be Windows, Unix, Linux, etc. In addition to the computer program capable of implementing the shaft cracking fault identification method executed by the electronic device disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks. The data 223 may include not only the data transmitted by the external device received by the electronic device, but also the data collected by its own input / output interface 25, etc.
[0117] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the shaft cracking fault identification method disclosed above is implemented. For the specific steps of this method, reference can be made to the corresponding content disclosed in the foregoing embodiments, and details will not be repeated here.
[0118] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts between the various embodiments, reference can be made to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and reference can be made to the description of the method part for related parts.
[0119] Those skilled in the art may further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application. The steps of the methods or algorithms described in combination with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of both. The software modules can be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable EPROM (Erasable Programmable Read Only Memory), electrically erasable programmable EEPROM (Electrically Erasable Programmable read only memory), registers, hard disks, removable disks, CD-ROM (Compact Disc Read-Only Memory), or any other form of storage medium known in the art.
[0120] Finally, it should also be noted that in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.
[0121] The above has introduced in detail a method, device, equipment and medium for identifying shaft cracking faults provided by the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.
Claims
1. A method for identifying shaft cracking faults, characterized in that, Including: Collecting the original vibration and shock data of the component to be measured within a preset time period; Preprocessing the original vibration and shock data to obtain various shock characteristic values of each single sample within the preset time period; wherein, various shock characteristic values include the shock characteristic intensity value of the driving gear, the shock characteristic intensity value of the double-sideband spectrum, the shock characteristic intensity value of the half-meshing spectrum, and the shock characteristic intensity value of the meshing spectrum; Obtaining multi-dimensional fault characteristic values according to various shock characteristic values; Identifying the shaft crack fault of the driving shaft according to the fault characteristic values to generate the fault result of the driving shaft.
2. The shaft cracking fault identification method according to claim 1, wherein The obtaining multi-dimensional fault characteristic values according to various shock characteristic values includes: Marking the samples with the shock characteristic intensity value of the driving gear greater than the first preset intensity threshold to obtain the first marked samples; Marking the samples with the shock characteristic intensity value of the double-sideband spectrum greater than the first preset intensity threshold to obtain the second marked samples, marking the samples with the shock characteristic intensity value of the meshing spectrum greater than the first preset intensity threshold to obtain the third marked samples, and marking the samples with the shock characteristic intensity value of the half-meshing spectrum greater than the first preset intensity threshold to obtain the fourth marked samples; Determining the average value of the shock characteristic intensity value of the half-meshing spectrum of the fourth marked samples; Determining the number of the first marked samples, the number of the second marked samples, the number of the third marked samples, and the average value of the shock characteristic intensity value of the half-meshing spectrum as the first fault characteristic value, the second fault characteristic value, the third fault characteristic value, and the fourth fault characteristic value respectively.
3. The shaft cracking fault recognition method according to claim 2, wherein Also including: If the driving shaft meets the first preset shaft crack symptom condition, generating a first fault result; wherein, the first preset shaft crack symptom condition is that the rotational speed at which the shock characteristic intensity value of the half-meshing spectrum appears in the fourth marked samples and the shock characteristic intensity value of the half-meshing spectrum both decrease with the passage of the operating time.
4. The shaft cracking fault identification method according to claim 3, characterized in that, The identifying the shaft crack fault of the driving shaft according to the fault characteristic values to generate the fault result of the driving shaft includes: If the driving shaft does not meet the first preset shaft crack symptom condition, judging whether the driving shaft meets the second preset shaft crack symptom condition based on the first fault characteristic value, the second fault characteristic value, the third fault characteristic value, and the fourth fault characteristic value; wherein, the second preset shaft crack symptom condition is that the fourth fault characteristic value is greater than the second preset intensity threshold and the first fault characteristic value, the second fault characteristic value, and the third fault characteristic value are all greater than the first preset quantity threshold; If it is determined that the driving shaft meets the second preset shaft crack symptom condition, generating a first fault result to perform fault warning based on the first fault result.
5. The shaft cracking fault identification method according to claim 3 or 4, characterized in that, The first fault result indicates that there is a shaft crack symptom in the driving shaft due to shaft fatigue.
6. The shaft cracking fault identification method according to claim 2, wherein, The identifying the shaft crack fault of the driving shaft according to the fault characteristic values to generate the fault result of the driving shaft includes: If the driving shaft meets the first preset shaft crack symptom condition and the second preset shaft crack symptom condition, determining that the driving shaft meets the first preset shaft crack fault diagnosis condition and generating a second fault result; Among them, the first preset shaft cracking symptom condition is that the rotational speed at which the semi-meshing spectrum impact characteristic intensity value appears in the fourth marked sample and the semi-meshing spectrum impact characteristic intensity value both decrease over time; the second preset shaft cracking symptom condition is that the fourth fault characteristic value is greater than the second preset intensity threshold and the first fault characteristic value, the second fault characteristic value, and the third fault characteristic value are all greater than the first preset quantity threshold.
7. The shaft cracking fault identification method according to claim 2, wherein The obtaining of multi-dimensional fault characteristic values according to various types of the impact characteristic values further includes: Screening out a double marked sample from the second marked sample and the third marked sample, where the impact characteristic intensity value of the two-soliton spectrum signal is greater than the third preset intensity threshold and the impact characteristic intensity value of the meshing spectrum signal is greater than the fourth preset intensity threshold, and determining the quantity of the double marked sample as the fifth fault characteristic value.
8. The shaft cracking fault recognition method according to claim 7, characterized in that The identifying of the shaft cracking fault of the driving shaft according to the fault characteristic values to generate the fault result of the driving shaft includes: If the fifth fault characteristic value is greater than the second preset quantity threshold, it is determined that the driving shaft meets the second preset shaft cracking fault diagnosis condition, and a second fault result is generated for fault alarm based on the second fault result.
9. The shaft crack fault identification method according to claim 6 or 8, characterized in that, The second fault result indicates that the driving shaft has a shaft cracking fault and the reason for the shaft cracking fault is stress concentration at the variable diameter transition circle between the bearing of the driving shaft and the driving gear; among them, the reason for the stress concentration at the variable diameter transition circle is that the driving shaft is subjected to a radial thrust from the driving gear.
10. The shaft crack fault identification method according to any one of claims 1 to 9, characterized in that, The preprocessing of the original vibration impact data to obtain various types of impact characteristic values of each single sample within the preset time period includes: Performing sampling processing on the original impact data to convert a continuous-time signal into a discrete-time signal; Performing Fourier transform on the discrete-time signal to convert the discrete-time signal from the time domain to the frequency domain, obtaining an initial frequency domain signal, and extracting the spectrum information of the initial frequency domain signal; Performing filtering processing on the initial frequency domain signal to remove noise signals, obtaining a filtered frequency domain signal; Performing normalization processing on the filtered frequency domain signal to eliminate the dimension difference, obtaining a normalized frequency domain signal; Performing feature extraction on the normalized frequency domain signal to obtain the impact characteristic values of each single sample.
11. An axle cracking fault identification device, characterized in that, It includes: A data acquisition module for acquiring the original vibration impact data of the component to be measured within a preset time period; A preprocessing module for preprocessing the original vibration impact data to obtain various types of impact characteristic values of each single sample within the preset time period; among them, various types of the impact characteristic values include the impact characteristic intensity value of the driving gear, the impact characteristic intensity value of the two-soliton spectrum, the impact characteristic intensity value of the semi-meshing spectrum, and the impact characteristic intensity value of the meshing spectrum; A fault characteristic value acquisition module for obtaining multi-dimensional fault characteristic values according to various types of the impact characteristic values; A fault identification module for identifying the shaft cracking fault of the driving shaft according to the fault characteristic values to generate the fault result of the driving shaft.
12. An electronic device, characterized in that, It includes: A memory for storing a computer program; A processor for executing the computer program to implement the steps of the shaft cracking fault identification method according to any one of claims 1 to 10.
13. A computer-readable storage medium, characterized in that, For storing a computer program; wherein, when the computer program is executed by a processor, the steps of the shaft cracking fault identification method according to any one of claims 1 to 10 are implemented.