Fault diagnosis method and device based on vibration spectrum and envelope spectrum

Abstract

The invention discloses a fault diagnosis method and device based on a vibration spectrum and an envelope spectrum, computer equipment and a storage medium, the method is mainly composed of characteristic value diagnosis, speed spectrum diagnosis and envelope spectrum diagnosis, and a fault model based on a water pump mechanism and analysis experience summarization are implanted into a software system. A software system is utilized to perform automatic diagnosis and analysis through a series of signal processing and analysis on collected signals, and equipment fault points are automatically judged through a computer. The method can automatically diagnose common unbalance faults, coupling misalignment faults, foundation loosening faults, water pump resonance faults, blade friction faults, bearing inner ring faults, bearing outer ring faults, poor bearing lubrication faults and the like of the water pump.

Description

Technical Field

[0001] The present application relates to the technical field of fault diagnosis, and in particular to a fault diagnosis method and device based on vibration spectrum and envelope spectrum. Background Art

[0002] Water pumps are one of the common industrial equipment and are widely used in industrial production. As water pumps are used, they often have various faults due to wear or improper use, such as unbalanced impellers, misaligned couplings, and bearing damage.

[0003] Usually, many devices are equipped with vibration, temperature and other sensors. At present, the fault diagnosis of water pump vibration is mainly done manually through the vibration spectrum collected by the sensor to diagnose and analyze the fault. Therefore, the personal experience of the diagnostic analyst is very important. However, on the one hand, due to different experience and analysis capabilities of analysts, the fault judgment capabilities vary. On the other hand, if the equipment needs to perform real-time fault diagnosis and analysis, a lot of manpower needs to be invested, and it also takes a lot of time and energy to train a professional diagnostic analyst.

[0004] In summary, it is urgent to propose a new water pump fault diagnosis method to solve the above problems. Summary of the invention

[0005] In order to solve the problems of the prior art, the present invention provides a fault diagnosis method, device, computer equipment and storage medium based on vibration spectrum and envelope spectrum to solve the problems existing in the fault diagnosis method of water pump in the prior art.

[0006] In order to solve one or more of the above technical problems, the technical solution adopted in this application is:

[0007] In a first aspect, a fault diagnosis method based on a vibration spectrum and an envelope spectrum is provided, the method comprising:

[0008] Acquire an acceleration waveform and a velocity spectrum of the device to be diagnosed, and extract a plurality of preset characteristic values ​​from the acceleration waveform and the velocity spectrum;

[0009] Comparing the plurality of preset characteristic values ​​with corresponding preset thresholds respectively;

[0010] When any of the preset characteristic values ​​exceeds the corresponding preset threshold value, the frequency of the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of multiple preset magnifications are obtained from the speed spectrum;

[0011] Determining whether the device to be diagnosed has a first type of fault according to the frequency of the maximum amplitude and the vibration amplitudes corresponding to the rotation speed values ​​of a plurality of preset magnifications and a preset analysis rule;

[0012] If the device to be diagnosed does not have the first type of fault, an envelope demodulation spectrum is obtained according to the acceleration waveform, and a demodulation value and an envelope effective value are calculated according to the envelope demodulation spectrum;

[0013] It is determined whether the device to be diagnosed has a second type of fault according to the demodulated value and the envelope effective value.

[0014] In a specific embodiment, obtaining the acceleration waveform and velocity spectrum of the device to be diagnosed includes:

[0015] Acquire a vibration acceleration signal of the device to be diagnosed, and generate an acceleration waveform according to the vibration acceleration signal;

[0016] Performing an integration operation on the acceleration waveform to obtain a velocity waveform;

[0017] The velocity waveform is subjected to fast Fourier transformation to obtain a velocity spectrum.

[0018] In a specific embodiment, extracting a plurality of preset characteristic values ​​from the acceleration waveform and the velocity spectrum includes:

[0019] Feature extraction is performed on the velocity spectrum to obtain the vibration severity, and the kurtosis and crest factor are obtained on the acceleration waveform.

[0020] In a specific embodiment, the vibration severity calculation formula is:

[0021] Xrms=sqrt(∑((X(i1)-Xa1)*(X(i1)-Xa1)) / N)

[0022] Xa1=∑X(i1) / N, X(i1) is the value corresponding to the acquisition point on the velocity spectrum, i1=1, 2...N, N is the acquisition number;

[0023] And / or, the kurtosis calculation formula is:

[0024] K=∑((X(i2)-Xa2)*(X(i2)-Xa2)*(X(i2)-Xa2)*(X(i2)-Xa2)) / N / Xrms

[0025] Wherein, Xa2=∑X(i2) / N, X(i2) is the value corresponding to the acquisition point on the acceleration waveform, i2=1, 2...N, N is the acquisition number;

[0026] The crest factor calculation formula is:

[0027] CF=Xp / Xrms

[0028] Wherein, Xp is the peak value of the acceleration waveform, and Xrms is the vibration intensity.

[0029] In a specific embodiment, when any of the preset characteristic values ​​exceeds the corresponding preset threshold, the frequency with the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of multiple preset magnifications are obtained from the speed spectrum, including:

[0030] The frequency of the maximum amplitude of the device to be diagnosed, the vibration amplitude corresponding to the first speed value, and the vibration amplitude corresponding to multiple second speed values ​​are obtained from the speed spectrum, wherein the second speed value is a multiple of the first speed value and the second speed value includes at least N times the speed value.

[0031] In a specific embodiment, judging whether the device to be diagnosed has a first type of fault according to the frequency of the maximum amplitude and the vibration amplitudes corresponding to the rotational speed values ​​of a plurality of preset magnifications and preset analysis rules includes:

[0032] Determining whether the device to be diagnosed has a resonance fault according to the frequency of the maximum amplitude and the resonance frequency of the device to be diagnosed;

[0033] If the device to be diagnosed does not have a resonance fault, judging whether the device to be diagnosed has an unbalance fault according to the vibration amplitude corresponding to the first speed value and the vibration severity;

[0034] If the device to be diagnosed does not have an unbalance fault, judging whether the device to be diagnosed has a blade friction fault according to the vibration amplitude corresponding to the N times speed value and the vibration severity;

[0035] If the device to be diagnosed does not have a blade friction fault, determining whether the device to be diagnosed has a misalignment fault according to the vibration amplitude corresponding to the first speed value, the vibration amplitude corresponding to one of the second speed values, and the vibration severity;

[0036] If the device to be diagnosed does not have a misalignment fault, determine whether the device to be diagnosed has a foundation loosening fault based on the vibration amplitude corresponding to the first speed value, the vibration amplitudes corresponding to multiple second speed values, and the vibration intensity.

[0037] In a specific embodiment, the second type of fault includes poor bearing lubrication, bearing outer ring fault, bearing inner ring fault and rolling element fault;

[0038] The step of obtaining an envelope demodulation spectrum according to the acceleration waveform, and calculating a demodulation value and an envelope effective value according to the envelope demodulation spectrum includes:

[0039] Selecting a target resonance frequency region on the acceleration waveform, performing preset processing on the resonance frequency region, and obtaining an envelope demodulation waveform containing a fault frequency, wherein a frequency f of the target resonance frequency region satisfies 0.5fmax≤f≤fmax, and fmax is a maximum resonance frequency of the device to be diagnosed;

[0040] Performing Fourier transformation on the envelope demodulation waveform to obtain an envelope demodulation spectrum;

[0041] The demodulation value and the effective value of the bearing outer ring envelope, the effective value of the bearing inner ring envelope and the effective value of the rolling element envelope are calculated according to the envelope demodulation spectrum.

[0042] In a second aspect, a fault diagnosis device based on a vibration spectrum and an envelope spectrum is also provided, the device comprising:

[0043] A first calculation module, used to obtain an acceleration waveform and a velocity spectrum of the device to be diagnosed, and extract a plurality of preset characteristic values ​​from the acceleration waveform and the velocity spectrum;

[0044] A first diagnostic module, used for comparing the plurality of preset characteristic values ​​with corresponding preset thresholds respectively;

[0045] A second calculation module is used to obtain the frequency of the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of multiple preset magnifications from the speed spectrum when any of the preset characteristic values ​​exceeds the corresponding preset threshold value;

[0046] A second diagnostic module, used for judging whether the device to be diagnosed has a first type of fault according to the frequency of the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of a plurality of preset magnifications and a preset analysis rule;

[0047] A third calculation module, configured to obtain an envelope demodulation spectrum according to the acceleration waveform if the device to be diagnosed does not have the first type of fault, and calculate a demodulation value and an envelope effective value according to the envelope demodulation spectrum;

[0048] A third diagnosis module is used to determine whether the device to be diagnosed has a second type of fault according to the demodulated value and the envelope effective value.

[0049] In a third aspect, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the computer program is executed by the processor, the fault diagnosis method based on the vibration spectrum and the envelope spectrum is implemented.

[0050] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed, the fault diagnosis method based on the vibration spectrum and the envelope spectrum is implemented.

[0051] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0052] The present application provides a fault diagnosis method, device, computer equipment and storage medium based on vibration spectrum and envelope spectrum. The method includes obtaining an acceleration waveform and a velocity spectrum of a device to be diagnosed, extracting a plurality of preset characteristic values ​​from the acceleration waveform and the velocity spectrum, comparing the plurality of preset characteristic values ​​with corresponding preset thresholds respectively, and when any of the preset characteristic values ​​exceeds the corresponding preset threshold, obtaining the frequency of the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of a plurality of preset magnifications from the velocity spectrum, and judging whether the device to be diagnosed has a first type of fault according to the frequency of the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of a plurality of preset magnifications and preset analysis rules; if the device to be diagnosed does not have the first type of fault, obtaining an envelope demodulation spectrum according to the acceleration waveform, and calculating a demodulation value and an envelope effective value according to the envelope demodulation spectrum, and judging whether the device to be diagnosed has a second type of fault according to the demodulation value and the envelope effective value. This application utilizes the experience summary of fault models and analysis based on the mechanism of water pumps to implant a software system, and utilizes the software system to perform automatic diagnosis and analysis through a series of signal processing and analysis on the collected signals. The computer automatically determines the equipment failure and can automatically diagnose common water pump imbalance failures, coupling misalignment failures, foundation looseness failures, water pump resonance failures, blade friction failures, bearing inner ring failures, bearing outer ring failures, and poor bearing lubrication failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 is a flow chart of a fault diagnosis method based on vibration spectrum and envelope spectrum provided in an embodiment of the present application;

[0055] Figure 2 is another flow chart of the fault diagnosis method based on vibration spectrum and envelope spectrum provided in an embodiment of the present application;

[0056] Figure 3It is a structural schematic diagram of a fault diagnosis device based on vibration spectrum and envelope spectrum provided in an embodiment of the present application;

[0057] Figure 4 It is an architectural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0059] As described in the background technology, the fault diagnosis of water pumps in the prior art mainly relies on manual analysis. On the one hand, analysts have different experiences and analysis capabilities, which leads to uneven fault judgment capabilities. On the other hand, if the equipment needs to perform real-time fault diagnosis and analysis, a large amount of manpower is required, and training a professional diagnostic analyst also requires a lot of time and energy. Therefore, the manual analysis method has the problems of being greatly affected by the personal experience of the analyst and requiring a lot of time and manpower.

[0060] To solve the above problems, the embodiment of the present application creatively proposes a new fault diagnosis method based on vibration spectrum and envelope spectrum, and uses the experience summary of fault model and analysis based on water pump mechanism to implant the software system. The software system uses the collected signals through a series of signal processing and analysis to perform automatic diagnosis and analysis. The computer automatically determines the equipment failure point, and can automatically diagnose common water pump imbalance failures, coupling misalignment failures, foundation looseness failures, water pump resonance failures, blade friction failures, bearing inner ring failures, bearing outer ring failures, and poor bearing lubrication failures.

[0061] The solution of the present application will be described in detail below in conjunction with the accompanying drawings and various embodiments.

[0062] Embodiment 1

[0063] The fault diagnosis method provided in the embodiment of the present application is based on the vibration spectrum and the envelope spectrum, and can be applied to the real-time automatic fault diagnosis of equipment such as water pumps. The method mainly consists of three parts: characteristic value diagnosis, velocity spectrum diagnosis, and envelope spectrum diagnosis. Figure 1 As shown, the method mainly includes the following processes:

[0064] Eigenvalue diagnostics:

[0065] Step 1: Obtain the real-time vibration acceleration signal of the equipment to be diagnosed, generate an acceleration waveform based on the vibration acceleration signal, and obtain a velocity waveform by integrating the acceleration waveform. Then, perform fast Fourier transform on the velocity waveform to obtain a velocity spectrum, extract eigenvalues ​​from the velocity spectrum, obtain the vibration intensity eigenvalues ​​of the real-time time domain waveform of the water pump, and obtain kurtosis, crest factor and other eigenvalues ​​on the acceleration waveform.

[0066] Among them, the equipment to be diagnosed in the embodiments of the present application includes but is not limited to a water pump, etc.

[0067] Specifically, the calculation formula for vibration severity is:

[0068] Xrms=sqrt(∑((X(i1)-Xa1)*(X(i1)-Xa1)) / N)

[0069] Xa1=∑X(i1) / N, X(i1) is the value corresponding to the acquisition point on the velocity spectrum, i1=1, 2...N, N is the acquisition number:

[0070] The calculation formula of kurtosis is:

[0071] K=∑((X(i2)-Xa2)*(X(i2)-Xa2)*(X(i2)-Xa2)*(X(i2)-Xa2)) / N / Xrms 4

[0072] Wherein, Xa=∑X(i2) / N, X(i2) is the value corresponding to the acquisition point on the acceleration waveform (i.e., the acceleration value corresponding to the acquisition point), i2=1, 2...N, N is the acquisition number;

[0073] The calculation formula of crest factor is:

[0074] CF=Xp / Xrms

[0075] Wherein, Xp is the peak value of the acceleration waveform, and Xrms is the root mean square value of the vibration acceleration (ie, the above-mentioned vibration severity).

[0076] It should be noted here that the present application does not make any improvements to the calculation formulas involved, such as integrals and fast Fourier transforms, and the calculation formulas in the prior art can be used, which will not be described in detail here.

[0077] Step 2: Set the thresholds for vibration severity, kurtosis, and crest factor.

[0078] Specifically, in the embodiments of the present application, there is no specific limitation on the specific values ​​of the thresholds of vibration intensity, kurtosis and crest factor, and users can set them according to actual needs.

[0079] Step 3: Compare the vibration severity, kurtosis and crest factor of the real-time time domain waveform of the water pump calculated in step 1 with the set threshold value. If the vibration severity, kurtosis and crest factor do not exceed the set threshold, it means that the equipment to be diagnosed is not faulty. If any one of the vibration severity, kurtosis and crest factor of the real-time time domain waveform of the water pump exceeds the set threshold, it means that the vibration amplitude of the equipment exceeds the standard and the speed spectrum diagnosis needs to be started.

[0080] Speed ​​spectrum diagnosis:

[0081] Step 4: Set the rotation speed value of the device to be diagnosed to RPM1, set the resonance frequency of the device to be diagnosed to Fn, and set the number of impellers of the device to be diagnosed to M.

[0082] Step 5: Find the vibration amplitudes corresponding to the rotation speed values ​​of multiple preset magnifications in the speed spectrum.

[0083] Specifically, the speed values ​​of multiple preset magnifications include the vibration amplitude corresponding to the first speed value and the vibration amplitude corresponding to multiple second speed values, wherein the second speed value is an integer multiple of the first speed value, and the second speed value includes at least N times the speed value, where N is the acquisition number. As a preferred example, the first speed value can be the speed value of the device to be diagnosed, and the speed value that is an integer multiple of the speed value of the device to be diagnosed is the second speed value. The second speed value (i.e., multiple preset magnifications) is not specifically limited in this application, and the user can set it according to actual needs. As a preferred example, the vibration amplitude corresponding to the second speed value includes but is not limited to a vibration amplitude Vrpm2 of 2 times RPM1, a vibration amplitude Vrpm3 of 3 times RPM1, a vibration amplitude Vrpm4 of 4 times RPM1, a vibration amplitude Vrpm5 of 5 times RPM1, a vibration amplitude Vrpm6 of 6 times RPM1, a vibration amplitude Vrpm7 of 7 times RPM1, a vibration amplitude Vrpm8 of 8 times RPM1, a vibration amplitude Vrpm9 of 9 times RPM1, a vibration amplitude Vrpm10 of 10 times RPM1...a vibration amplitude Vrpm50 of 50 times RPM1 and a vibration amplitude VrpmN of N times RPM1, etc., which are not elaborated here one by one.

[0084] Step 6: Resonance fault judgment: Get the frequency Fmax with the maximum amplitude in the speed spectrum. When the values ​​of Fmax and Fn are the same, it means that the equipment to be diagnosed has a resonance fault. When Fmax≠Fn, an unbalance fault judgment is performed;

[0085] Step 7: Unbalance fault judgment: When Fmax≠Fn, find the vibration amplitude Vrpm1 of the first speed value RPM1 in the speed spectrum. If Xrms is the vibration intensity obtained in step 1, it indicates that the equipment to be diagnosed has an imbalance fault. Otherwise, a water pump blade friction fault is determined.

[0086] Step 8: Water pump blade friction fault judgment: When When , find the vibration amplitude VrpmN corresponding to the N-fold speed value in the speed spectrum. If it is, it means that the equipment to be diagnosed has blade friction fault, otherwise it is judged as misalignment fault.

[0087] Step 9: Determine the misalignment fault: When the vibration amplitudes Vrpm1 and Vrpmx corresponding to the first speed value and one of the second speed values ​​are found in the speed spectrum, where x is a positive integer greater than 1, and the specific value of x can be set according to actual needs and is not limited here. When the condition is satisfied If it is, it means that the equipment to be diagnosed has a misalignment fault, otherwise it is judged as a loose foundation fault.

[0088] Step 10: Loose foundation fault judgment: When the vibration amplitudes corresponding to multiple second speed values ​​are found in the speed spectrum, when When , it indicates that the equipment to be diagnosed has a loose foundation fault, where x<y≤50.

[0089] If the equipment to be diagnosed does not have the above-mentioned resonance fault, imbalance fault, pump blade friction fault, misalignment fault and foundation looseness fault, it is necessary to start the envelope spectrum diagnosis.

[0090] Envelope spectrum diagnosis:

[0091] Step 11: Select the target resonance frequency region on the acceleration waveform, obtain the envelope demodulation waveform containing the fault frequency through signal processing, filtering, translation and transformation, and then obtain the envelope demodulation spectrum by Fourier transforming the envelope demodulation waveform.

[0092] Specifically, the embodiment of the present application does not specifically limit the selection method of the target resonance frequency zone. As a preferred example, the selection of the resonance frequency zone can be determined according to the hardware of the device to be diagnosed, such as the device to be diagnosed. It is further preferred that the selection can be made according to the maximum resonance frequency of the device to be diagnosed, and the frequency f of the selected target resonance frequency zone satisfies 0.5fmax≤f≤fmax, where fmax is the maximum resonance frequency of the device to be diagnosed. For example, when the maximum resonance frequency of the device to be diagnosed is 1000hz, the target resonance frequency zone is 500hz-1000hz.

[0093] Step 12: Calculate the demodulation value from the envelope demodulation spectrum. The calculation formula is as follows:

[0094] Xge=sqrt(∑((Y(j)-Ya)*(Y(j)-Ya)) / L)

[0095] Wherein, Ya=∑Y(j) / L, Y(j) is the value corresponding to the acquisition point on the envelope demodulation spectrum, j=1, 2...L, and L is the acquisition number.

[0096] Step 13: Calculate the bearing damage frequency, where bearing damage is divided into three types: outer ring failure, inner ring failure, and rolling element failure.

[0097] Specifically, the calculation formula of the fault characteristic frequency of the rolling element fault (abbreviated as FTF) is:

[0098]

[0099] The calculation formula of the fault characteristic frequency of the outer race fault (BPFO) is:

[0100]

[0101] The calculation formula of the fault characteristic frequency of the inner race fault (BPFI) is:

[0102]

[0103] Where D0 is the median diameter of the bearing (mm), d is the roller diameter (mm), A is the contact angle of the roller (°), Z is the number of rollers, and fn is the rotational frequency of the inner ring of the bearing relative to the outer ring (Hz).

[0104] Step 14: Obtain vibration amplitudes of the inner ring, outer ring, and rolling element damage frequencies at multiple magnifications in the envelope demodulation spectrum.

[0105] Specifically, the vibration amplitudes of the inner ring damage frequencies of multiple magnifications are recorded as: GE1bpfo, GE2bpfo, GE3bpfo...GEλbpfo:

[0106] The vibration amplitudes of the outer ring damage frequencies at multiple magnifications GE1bpfi, GE2bpfi, GE3bpfi...GEλbpfi:

[0107] The vibration amplitudes of the rolling element damage frequencies of multiple magnifications are GE1ftf, GE2fff, GE3fff...GEλftf.

[0108] Here, λ≤50 and λ is an integer.

[0109] Step 15: Calculate the envelope effective values ​​of the damage frequencies of the inner ring, outer ring and rolling element respectively.

[0110] Among them, the calculation formula of the effective value of the inner circle envelope is:

[0111]

[0112] The calculation formula of the outer ring envelope effect value is:

[0113]

[0114] The calculation formula of the effective value of the rolling element envelope is:

[0115]

[0116] Step 17: Determine whether the equipment to be diagnosed has a bearing fault based on the demodulated value and the envelope effective value.

[0117] when Determine that the equipment to be diagnosed has a bearing lubrication failure;

[0118] when When the fault occurs, it is determined that the equipment to be diagnosed has a bearing outer ring fault;

[0119] when When the fault occurs, it is determined that the equipment to be diagnosed has a bearing inner ring fault;

[0120] when When the device to be diagnosed has a rolling element failure, it is determined that the device to be diagnosed has a rolling element failure.

[0121] Wherein, Xge is the demodulated value calculated in the above step twelve, wherein 50%≤ω1≤100%, 0≤ω2≤50%.

[0122] Embodiment 2

[0123] Corresponding to the above-mentioned embodiment 1, the present invention further provides a fault diagnosis method based on vibration spectrum and envelope spectrum, wherein in this embodiment, the same or similar contents as those of the above-mentioned embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 The method comprises the following steps:

[0124] S100: Acquire an acceleration waveform and a velocity spectrum of a device to be diagnosed, and extract a plurality of preset characteristic values ​​from the acceleration waveform and the velocity spectrum;

[0125] S200: Compare the plurality of preset characteristic values ​​with corresponding preset thresholds respectively.

[0126] S300: When any of the preset characteristic values ​​exceeds the corresponding preset threshold, the frequency of the maximum amplitude and the vibration amplitudes corresponding to the rotation speed values ​​of a plurality of preset magnifications are obtained from the speed spectrum;

[0127] S400: judging whether the device to be diagnosed has a first type of fault according to the frequency of the maximum amplitude and the vibration amplitudes corresponding to the rotation speed values ​​of a plurality of preset magnifications and a preset analysis rule;

[0128] S500: If the device to be diagnosed does not have the first type of fault, obtain an envelope demodulation spectrum according to the acceleration waveform, and calculate a demodulation value and an envelope effective value according to the envelope demodulation spectrum;

[0129] S600: Determine whether the device to be diagnosed has a second type of fault according to the demodulated value and the envelope effective value.

[0130] Specifically, the preset characteristic values ​​include but are not limited to the characteristic values ​​such as vibration severity, kurtosis and crest factor. The first type of fault includes but is not limited to resonance fault, imbalance fault, blade friction fault, misalignment fault and foundation loose fault. The second type of fault includes but is not limited to poor bearing lubrication fault, bearing outer ring fault, bearing inner ring fault and rolling element fault.

[0131] As a preferred implementation, in the embodiment of the present application, the acquisition of the acceleration waveform and velocity spectrum of the device to be diagnosed includes:

[0132] S101: Acquire a real-time vibration acceleration signal of a device to be diagnosed, and generate an acceleration waveform according to the vibration acceleration signal;

[0133] S102: performing an integration operation on the acceleration waveform to obtain a velocity waveform;

[0134] S103: Performing fast Fourier transform on the velocity waveform to obtain a velocity spectrum.

[0135] Specifically, the present application does not make any improvements to the calculation formulas involved, such as integrals and fast Fourier transforms, and the calculation formulas in the prior art can be used, which will not be described in detail here.

[0136] As a preferred implementation, in the embodiment of the present application, extracting a plurality of preset characteristic values ​​from the acceleration waveform and the velocity spectrum includes:

[0137] Feature extraction is performed on the velocity spectrum to obtain the vibration severity, and the kurtosis and crest factor are obtained on the acceleration waveform.

[0138] The vibration intensity calculation formula is:

[0139] Xrms=sqrt(∑((X(i1)-Xa1)*(X(i1)-Xa1)) / N)

[0140] Xa1=∑X(i1) / N, X(i1) is the value corresponding to the acquisition point on the velocity spectrum, i1=1, 2...N, N is the acquisition number;

[0141] And / or, the kurtosis calculation formula is:

[0142] K=∑((X(i2)-Xa2)*(X(i2)-Xa2)*(X(i2)-Xa2)*(X(i2)-Xa2)) / N / Xrms 4

[0143] Wherein, Xa=∑X(i2) / N, X(i2) is the value corresponding to the acquisition point on the acceleration waveform, i2=1, 2...N, N is the acquisition number;

[0144] The crest factor calculation formula is:

[0145] CF=Xp / Xms

[0146] Wherein, Xp is the peak value of the acceleration waveform, and Xrms is the root mean square value of the vibration acceleration (ie, the above-mentioned vibration severity).

[0147] As a preferred implementation, in the embodiment of the present application, when any of the preset characteristic values ​​exceeds the corresponding preset threshold value, the frequency of the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of multiple preset magnifications are obtained from the speed spectrum, including:

[0148] The frequency of the maximum amplitude of the device to be diagnosed, and the vibration amplitudes corresponding to the first and multiple second speed values ​​are obtained from the speed spectrum, wherein the second speed value is in a multiple relationship with the first speed value and the second speed value includes at least N times the speed value.

[0149] As a preferred implementation, in the embodiment of the present application, judging whether the device to be diagnosed has a first type of fault according to the frequency of the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of multiple preset magnifications and preset analysis rules includes:

[0150] Determining whether the device to be diagnosed has a resonance fault according to the frequency of the maximum amplitude and the resonance frequency of the device to be diagnosed;

[0151] If the device to be diagnosed does not have a resonance fault, judging whether the device to be diagnosed has an unbalance fault according to the vibration amplitude corresponding to the first speed value and the vibration severity;

[0152] If the device to be diagnosed does not have an unbalance fault, determine whether the device to be diagnosed has a blade friction fault according to the vibration amplitude corresponding to the N times speed value and the vibration severity:

[0153] If the device to be diagnosed does not have a blade friction fault, determining whether the device to be diagnosed has a misalignment fault according to the first speed value, the vibration amplitude corresponding to one of the second speed values, and the vibration severity;

[0154] If the device to be diagnosed does not have a misalignment fault, it is determined whether the device to be diagnosed has a foundation loosening fault according to the first speed value, the vibration amplitudes corresponding to the plurality of second speed values, and the vibration severity.

[0155] Specifically, the specific judgment methods for resonance fault, imbalance fault, blade friction fault, misalignment fault and foundation looseness fault can be referred to the relevant contents of implementation one, and will not be repeated here one by one.

[0156] As a preferred implementation, in the embodiment of the present application, the second type of fault includes poor bearing lubrication, bearing outer ring fault, bearing inner ring fault and bearing rolling element fault;

[0157] The step of obtaining an envelope demodulation spectrum according to the acceleration waveform, and calculating a demodulation value and an envelope effective value according to the envelope demodulation spectrum includes:

[0158] Selecting a target resonance frequency region on the acceleration waveform, performing preset processing on the resonance frequency region, and obtaining an envelope demodulation waveform containing a fault frequency, wherein a frequency f of the target resonance frequency region satisfies 0.5fmax≤f≤fmax, and fmax is a maximum resonance frequency of the device to be diagnosed;

[0159] Performing Fourier transformation on the envelope demodulation waveform to obtain an envelope demodulation spectrum;

[0160] The demodulation value and the effective values ​​of the bearing outer ring, inner ring and rolling element envelope are calculated based on the envelope demodulation spectrum.

[0161] Similarly, the specific judgment methods for poor bearing lubrication, bearing outer ring failure, bearing inner ring failure and bearing rolling element failure can be referred to the relevant contents of implementation one, and will not be repeated here.

[0162] Embodiment 3

[0163] Corresponding to the above-mentioned embodiments 1 and 2, the present invention further provides a fault diagnosis device based on vibration spectrum and envelope spectrum, wherein in this embodiment, the same or similar contents as those of the above-mentioned embodiments 1 or 2 can be referred to the above introduction and will not be described in detail later. Figure 3 The device comprises:

[0164] A first calculation module, used to obtain an acceleration waveform and a velocity spectrum of the device to be diagnosed, and extract a plurality of preset characteristic values ​​from the acceleration waveform and the velocity spectrum;

[0165] A first diagnostic module, used for comparing the plurality of preset characteristic values ​​with corresponding preset thresholds respectively;

[0166] A second calculation module is used to obtain the frequency of the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of multiple preset magnifications from the speed spectrum when any of the preset characteristic values ​​exceeds the corresponding preset threshold value;

[0167] A second diagnostic module, used for judging whether the device to be diagnosed has a first type of fault according to the frequency of the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of a plurality of preset magnifications and a preset analysis rule;

[0168] A third calculation module, configured to obtain an envelope demodulation spectrum according to the acceleration waveform if the device to be diagnosed does not have the first type of fault, and calculate a demodulation value and an envelope effective value according to the envelope demodulation spectrum;

[0169] A third diagnosis module is used to determine whether the device to be diagnosed has a second type of fault according to the demodulated value and the envelope effective value.

[0170] As a preferred implementation, in the embodiment of the present application, the first calculation module is specifically used for:

[0171] Acquire a vibration acceleration signal of the device to be diagnosed, and generate an acceleration waveform according to the vibration acceleration signal;

[0172] Performing an integration operation on the acceleration waveform to obtain a velocity waveform;

[0173] The velocity waveform is subjected to fast Fourier transformation to obtain a velocity spectrum.

[0174] As a preferred implementation, in the embodiment of the present application, the first calculation module is also used for:

[0175] Feature extraction is performed on the velocity spectrum to obtain the vibration severity, and the kurtosis and crest factor are obtained on the acceleration waveform.

[0176] As a preferred implementation, in the embodiment of the present application, the vibration intensity calculation formula is:

[0177] Xrms=sqrt(∑((X(i1)-Xa1)*(X(i1)-Xa1)) / N)

[0178] Xa1=∑X(i1) / N, X(i1) is the value corresponding to the acquisition point on the velocity spectrum, i1=1, 2...N, N is the acquisition number;

[0179] And / or, the kurtosis calculation formula is:

[0180] K=∑((X(i2)-Xa2)*(X(i2)-Xa2)*(X(i2)-Xa2)*(X(i2)-Xa2)) / N / Xrms 4

[0181] Wherein, Xa=∑X(i2) / N, X(i2) is the value corresponding to the acquisition point on the acceleration waveform, i2=1, 2...N, N is the acquisition number;

[0182] The crest factor calculation formula is:

[0183] CF=Xp / Xrms

[0184] Wherein, Xp is the peak value of the acceleration waveform, and Xrms is the root mean square value of the vibration acceleration (ie, the vibration severity).

[0185] As a preferred implementation, in the embodiment of the present application, the second calculation module is specifically used for:

[0186] The frequency of the maximum amplitude of the device to be diagnosed, the vibration amplitude corresponding to the first speed value, and the vibration amplitude corresponding to multiple second speed values ​​are obtained from the speed spectrum, wherein the second speed value is a multiple of the first speed value and the second speed value includes at least N times the speed value.

[0187] As a preferred implementation, in the embodiment of the present application, the second diagnostic module is specifically used for:

[0188] Determining whether the device to be diagnosed has a resonance fault according to the frequency of the maximum amplitude and the resonance frequency of the device to be diagnosed;

[0189] If the device to be diagnosed does not have a resonance fault, judging whether the device to be diagnosed has an unbalance fault according to the vibration amplitude corresponding to the first speed value and the vibration severity;

[0190] If the device to be diagnosed does not have an unbalance fault, judging whether the device to be diagnosed has a blade friction fault according to the vibration amplitude corresponding to the N times speed value and the vibration severity;

[0191] If the device to be diagnosed does not have a blade friction fault, judging whether the device to be diagnosed has a misalignment fault according to the vibration amplitude corresponding to the first speed value, the vibration amplitude corresponding to one of the second speed values, and the vibration severity;

[0192] If the device to be diagnosed does not have a misalignment fault, it is determined whether the device to be diagnosed has a foundation loosening fault according to the first speed value, the vibration amplitudes corresponding to the plurality of second speed values, and the vibration severity.

[0193] As a preferred implementation, in the embodiment of the present application, the second type of fault includes poor bearing lubrication, bearing outer ring fault, bearing inner ring fault and bearing rolling element fault;

[0194] The third calculation module is specifically used for:

[0195] Selecting a target resonance frequency region on the acceleration waveform, performing preset processing on the resonance frequency region, and obtaining an envelope demodulation waveform containing a fault frequency, wherein a frequency f of the target resonance frequency region satisfies 0.5fmax≤f≤fmax, and fmax is a maximum resonance frequency of the device to be diagnosed;

[0196] Performing Fourier transformation on the envelope demodulation waveform to obtain an envelope demodulation spectrum;

[0197] The demodulation value and the effective value of the bearing outer ring envelope, the effective value of the bearing inner ring envelope and the effective value of the rolling element envelope are calculated according to the envelope demodulation spectrum.

[0198] Embodiment 4

[0199] Corresponding to the above-mentioned embodiments one to three, the present invention also provides a computer device, including: a processor and a memory, the memory storing a computer program that can be run on the processor, and when the computer program is executed by the processor, the fault diagnosis method based on the vibration spectrum and envelope spectrum provided in any one of the above-mentioned embodiments is executed.

[0200] in, Figure 4 The computer device is shown as an example, and may specifically include a processor 1510, a video display adapter 1511, a disk drive 1512, an input / output interface 1513, a network interface 1514, and a memory 1520. The processor 1510, the video display adapter 1511, the disk drive 1512, the input / output interface 1513, the network interface 1514, and the memory 1520 may be communicatively connected via a communication bus 1530.

[0201] Among them, the processor 1510 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc., to execute relevant programs to implement the technical solution provided by the present invention.

[0202] The memory 1520 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1520 can store an operating system 1521 for controlling the operation of the electronic device and a basic input and output system (BIOS) for controlling the low-level operation of the electronic device. In addition, a web browser 1523, a data storage management system 1524, and a device identification information processing system 1525, etc. can also be stored. The above-mentioned device identification information processing system 1525 can be an application program that specifically implements the operations of the aforementioned steps in the embodiment of the present invention. In short, when the technical solution provided by the present invention is implemented by software or firmware, the relevant program code is stored in the memory 1520 and is called and executed by the processor 1510.

[0203] The input / output interface 1513 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0204] The network interface 1514 is used to connect to a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0205] The bus includes a path that transmits information between the various components of the device (eg, processor 1510, video display adapter 1511, disk drive 1512, input / output interface 1513, network interface 1514, and memory 1520).

[0206] In addition, the electronic device can also obtain information on specific collection conditions from the virtual resource object collection condition information database for use in condition judgment, etc.

[0207] It should be noted that, although the above device only shows a processor 1510, a video display adapter 1511, a disk drive 1512, an input / output interface 1513, a network interface 1514, a memory 1520, a bus, etc., in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include components necessary for implementing the solution of the present invention, and does not necessarily include all the components shown in the figure.

[0208] Embodiment 5

[0209] Corresponding to the above-mentioned embodiments 1 to 4, an embodiment of the present invention further provides a computer-readable storage medium, wherein, in this embodiment, the same or similar contents as those of the above-mentioned embodiments 1 to 4 can be referred to the above introduction and will not be repeated later.

[0210] The computer readable storage medium stores a computer program, and when the computer program is executed by the processor, the following steps are implemented:

[0211] Acquire an acceleration waveform and a velocity spectrum of the device to be diagnosed, and extract a plurality of preset characteristic values ​​from the acceleration waveform and the velocity spectrum;

[0212] Comparing the plurality of preset characteristic values ​​with corresponding preset thresholds respectively;

[0213] When any of the preset characteristic values ​​exceeds the corresponding preset threshold value, the frequency of the maximum amplitude and the vibration amplitudes corresponding to the rotation speed values ​​of multiple preset magnifications are obtained from the speed spectrum;

[0214] Determining whether the device to be diagnosed has a first type of fault according to the frequency of the maximum amplitude and the vibration amplitudes corresponding to the rotation speed values ​​of a plurality of preset magnifications and a preset analysis rule;

[0215] If the device to be diagnosed does not have the first type of fault, an envelope demodulation spectrum is obtained according to the acceleration waveform, and a demodulation value and an envelope effective value are calculated according to the envelope demodulation spectrum;

[0216] It is determined whether the device to be diagnosed has a second type of fault according to the demodulated value and the envelope effective value.

[0217] In some implementations, in the embodiments of the present application, when the computer program is executed by the processor, the steps corresponding to the method described in Embodiment 1 may also be implemented. Please refer to the detailed description in Embodiment 1 and no further details will be given here.

[0218] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present invention or certain parts of the embodiments.

[0219] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0220] The technical solution provided by the present invention is described in detail above. The principle and implementation method of the present invention are described in detail using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A fault diagnosis method based on vibration spectrum and envelope spectrum, characterized in that: The method comprises: Acquire an acceleration waveform and a velocity spectrum of the device to be diagnosed, and extract a plurality of preset characteristic values ​​from the acceleration waveform and the velocity spectrum; Comparing the plurality of preset characteristic values ​​with corresponding preset thresholds respectively; When any of the preset characteristic values ​​exceeds the corresponding preset threshold value, the frequency of the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of multiple preset magnifications are obtained from the speed spectrum; Determining whether the device to be diagnosed has a first type of fault according to the frequency of the maximum amplitude and the vibration amplitudes corresponding to the rotation speed values ​​of a plurality of preset magnifications and a preset analysis rule; If the device to be diagnosed does not have the first type of fault, an envelope demodulation spectrum is obtained according to the acceleration waveform, and a demodulation value and an envelope effective value are calculated according to the envelope demodulation spectrum; It is determined whether the device to be diagnosed has a second type of fault according to the demodulated value and the envelope effective value.

2. The fault diagnosis method based on vibration spectrum and envelope spectrum according to claim 1 is characterized in that: The step of obtaining the acceleration waveform and velocity spectrum of the device to be diagnosed comprises: Acquire a vibration acceleration signal of the device to be diagnosed, and generate an acceleration waveform according to the vibration acceleration signal; Performing an integration operation on the acceleration waveform to obtain a velocity waveform; The velocity waveform is subjected to fast Fourier transformation to obtain a velocity spectrum.

3. The fault diagnosis method based on vibration spectrum and envelope spectrum according to claim 1 or 2, characterized in that: Extracting a plurality of preset characteristic values ​​from the acceleration waveform and the velocity spectrum comprises: Feature extraction is performed on the velocity spectrum to obtain the vibration severity, and the kurtosis and crest factor are obtained on the acceleration waveform.

4. The fault diagnosis method based on vibration spectrum and envelope spectrum according to claim 3 is characterized in that: The vibration intensity calculation formula is: Xrms=sqrt(∑((X(i1)-Xa1)*(X(i1)-Xa1)) / N) Xa1=∑X(i1) / N, X(i1) is the value corresponding to the acquisition point on the velocity spectrum, i1=1, 2...N, N is the acquisition number; And / or, the kurtosis calculation formula is: K=∑((X(i2)-Xa2)*(X(i2)-Xa2)*(X(i2)-Xa2)*(X(i2)-Xa2)) / N / Xrms 4 Wherein, Xa2=∑X(i2) / N, X(i2) is the value corresponding to the acquisition point on the acceleration waveform, i2=1, 2...N, N is the acquisition number; The crest factor calculation formula is: CF=Xp / Xrms Wherein, Xp is the peak value of the acceleration waveform, and Xrms is the vibration severity.

5. The fault diagnosis method based on vibration spectrum and envelope spectrum according to claim 4 is characterized in that: When any of the preset characteristic values ​​exceeds the corresponding preset threshold, the frequency with the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of multiple preset magnifications are obtained from the speed spectrum, including: The frequency of the maximum amplitude of the device to be diagnosed, the vibration amplitude corresponding to the first speed value, and the vibration amplitude corresponding to multiple second speed values ​​are obtained from the speed spectrum, wherein the second speed value is a multiple of the first speed value and the second speed value includes at least N times the speed value.

6. The fault diagnosis method based on vibration spectrum and envelope spectrum according to claim 5 is characterized in that: The step of judging whether the device to be diagnosed has a first type of fault according to the frequency of the maximum amplitude and the vibration amplitudes corresponding to the rotation speed values ​​of a plurality of preset magnifications and a preset analysis rule comprises: Determining whether the device to be diagnosed has a resonance fault according to the frequency of the maximum amplitude and the resonance frequency of the device to be diagnosed; If the device to be diagnosed does not have a resonance fault, judging whether the device to be diagnosed has an unbalance fault according to the vibration amplitude corresponding to the first speed value and the vibration severity; If the device to be diagnosed does not have an unbalance fault, judging whether the device to be diagnosed has a blade friction fault according to the vibration amplitude corresponding to the N times speed value and the vibration severity; If the device to be diagnosed does not have a blade friction fault, judging whether the device to be diagnosed has a misalignment fault according to the vibration amplitude corresponding to the first speed value, the vibration amplitude corresponding to one of the second speed values, and the vibration severity; If the device to be diagnosed does not have a misalignment fault, it is determined whether the device to be diagnosed has a foundation loosening fault according to the vibration amplitude corresponding to the first speed value, the vibration amplitudes corresponding to the plurality of second speed values, and the vibration severity.

7. The fault diagnosis method based on vibration spectrum and envelope spectrum according to claim 1 or 2, characterized in that: The second type of faults include poor bearing lubrication, bearing outer ring fault, bearing inner ring fault and rolling element fault; The step of obtaining an envelope demodulation spectrum according to the acceleration waveform, and calculating a demodulation value and an envelope effective value according to the envelope demodulation spectrum includes: Selecting a target resonance frequency region on the acceleration waveform, performing preset processing on the resonance frequency region, and obtaining an envelope demodulation waveform containing a fault frequency, wherein a frequency f of the target resonance frequency region satisfies 0.5fmax≤f≤fmax, and fmax is a maximum resonance frequency of the device to be diagnosed; Performing Fourier transformation on the envelope demodulation waveform to obtain an envelope demodulation spectrum; The demodulation value and the effective value of the bearing outer ring envelope, the effective value of the bearing inner ring envelope and the effective value of the rolling element envelope are calculated according to the envelope demodulation spectrum.

8. A fault diagnosis device based on vibration spectrum and envelope spectrum, characterized in that: The device comprises: A first calculation module, used to obtain an acceleration waveform and a velocity spectrum of the device to be diagnosed, and extract a plurality of preset characteristic values ​​from the acceleration waveform and the velocity spectrum; A first diagnostic module, used for comparing the plurality of preset characteristic values ​​with corresponding preset thresholds respectively; A second calculation module is used to obtain the frequency of the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of multiple preset magnifications from the speed spectrum when any of the preset characteristic values ​​exceeds the corresponding preset threshold value; A second diagnostic module, used for judging whether the device to be diagnosed has a first type of fault according to the frequency of the maximum amplitude and the vibration amplitude corresponding to the rotation speed values ​​of a plurality of preset magnifications and a preset analysis rule; A third calculation module, configured to obtain an envelope demodulation spectrum according to the acceleration waveform if the device to be diagnosed does not have the first type of fault, and calculate a demodulation value and an envelope effective value according to the envelope demodulation spectrum; A third diagnosis module is used to determine whether the device to be diagnosed has a second type of fault according to the demodulated value and the envelope effective value.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the computer program is executed by the processor, the fault diagnosis method based on the vibration spectrum and envelope spectrum described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, characterized in that: When the computer program is executed, the fault diagnosis method based on the vibration spectrum and envelope spectrum according to any one of claims 1 to 7 is implemented.

Images