CN110174281A - A kind of electromechanical equipment fault diagnosis method and system - Google Patents
A kind of electromechanical equipment fault diagnosis method and system Download PDFInfo
- Publication number
- CN110174281A CN110174281A CN201910487476.5A CN201910487476A CN110174281A CN 110174281 A CN110174281 A CN 110174281A CN 201910487476 A CN201910487476 A CN 201910487476A CN 110174281 A CN110174281 A CN 110174281A
- Authority
- CN
- China
- Prior art keywords
- signal
- electromechanical equipment
- cloud
- noise reduction
- vibration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a kind of electromechanical equipment fault diagnosis method and system, different measuring points are equipped with vibrating speed sensors and vibration acceleration sensor on the electromechanical equipment bearing vertical direction, the vibrating speed sensors and the vibration acceleration sensor are for acquiring vibration signal, this method comprises: the vibration signal is sent to cloud by the electromechanical equipment；The cloud carries out median filtering to the vibration signal and wavelet-packet noise reduction is handled, the signal after obtaining noise reduction；The cloud carries out cepstrum analysis to the signal after the noise reduction, obtains scramble spectrum signal；The cloud carries out fault diagnosis according to the scramble spectrum signal.Electromechanical equipment fault diagnosis method and system provided by the invention improve the accuracy of fault diagnosis for solving the technical issues of prior art method for diagnosing faults cannot detect electromechanical equipment imbalance, misalign.
Description
Technical field
The present invention relates to fault diagnosis technology field, in particular to a kind of electromechanical equipment fault diagnosis method and system.
Background technique
In steel, coal mine, in the modern devices of the large and medium-sized enterprise such as petrochemical industry, various large complicated mechanical equipments such as subtract fixed
The mechanical, electrical machine of diameter, pump class, blower, air compressor machine, gear-box etc. play very important effect.With the development of technology and equipment
The continuous modernization of management, for sunykatuib analysis digital assay technology till now of the analysis since most of instrument failure,
The speed and performance of analysis are all greatly improved.
Oil analyzing technology is the mill of the performance change and carrying by lubricant used in analytical technology or working media
The case where damaging particle, so that the lubrication of equipment and the information of state of wear are obtained, the working condition and prediction failure of valuator device,
So that it is determined that failure cause, type and the technology of position.But oil analyzing technology can only pass through the wear-out diagnosis of analysis particle
Lubricating oil analysis, gear engagement and the problem of bearing fault out, can not be diagnosed to be that electromechanical equipment is uneven, asking of misaligning
Topic.
Temperature diagnostic is to judge electromechanical equipment with the presence or absence of failure by monitoring device temperature of key part.But temperature
Diagnosis the problem of can only detecting bearing fault and lubricating oil analysis, can not detect electromechanical equipment is uneven, misalign and
The problem of gear engages.
Summary of the invention
The present invention provides a kind of electromechanical equipment fault diagnosis method and system, for solving prior art method for diagnosing faults
The technical issues of cannot detecting electromechanical equipment imbalance, misaligning, improve the accuracy of fault diagnosis.
In a first aspect, the embodiment of the invention provides a kind of electromechanical equipment method for diagnosing faults, the electromechanical equipment bearing
Different measuring points are equipped with vibrating speed sensors and vibration acceleration sensor on vertical direction, the vibrating speed sensors and
The vibration acceleration sensor is used to acquire vibration signal, this method comprises:
The vibration signal is sent to cloud by the electromechanical equipment；
The cloud carries out median filtering to the vibration signal and wavelet-packet noise reduction is handled, the signal after obtaining noise reduction；
The cloud carries out cepstrum analysis to the signal after the noise reduction, obtains scramble spectrum signal；
The cloud carries out fault diagnosis according to the scramble spectrum signal.
Preferably, the cloud carries out median filtering to the vibration signal, specifically: obtain adopting for the vibration signal
Sample frequency calculates the window width of median filter according to the sample frequency, is filtered according to the window width.
Preferably, the cloud carries out median filtering to the vibration signal and wavelet-packet noise reduction is handled, specifically: centering
Signal after value filtering carries out WAVELET PACKET DECOMPOSITION, wavelet packet coefficient and best wavelet packet basis is determined, according to preset threshold value to institute
It states wavelet packet coefficient to be handled, obtains new wavelet packet coefficient, according to the new wavelet packet coefficient and the best wavelet packet basis
Carry out signal reconstruction, the signal after obtaining noise reduction.
Preferably, the cloud carries out cepstrum analysis to the signal after the noise reduction, obtains scramble spectrum signal, specifically
Are as follows: the signal after the noise reduction is subjected to Fourier transformation, obtains frequency spectral function, to the logarithm of the frequency spectral function into
Row inverse Fourier transform obtains scramble spectrum signal.
Preferably, operation trend of the cloud according to the scramble spectrum signal to the electromechanical equipment is further comprised the steps of:
It is predicted, the operation trend includes loss rank and remaining life.
Second aspect, the embodiment of the invention provides a kind of electromechanical equipment fault diagnosis systems, including electromechanical equipment and cloud
It holds, different measuring points are equipped with vibrating speed sensors and vibration acceleration sensor on the electromechanical equipment bearing vertical direction,
For acquiring vibration signal, which includes: for the vibrating speed sensors and the vibration acceleration sensor
The electromechanical equipment is used to the vibration signal being sent to cloud；
The cloud is used to carry out median filtering to the vibration signal and wavelet-packet noise reduction is handled, the letter after obtaining noise reduction
Number；
The cloud is used to carry out cepstrum analysis to the signal after the noise reduction, obtains scramble spectrum signal；
The cloud is used to carry out fault diagnosis according to the scramble spectrum signal.
Preferably, the cloud is used to carry out median filtering to the vibration signal, specifically: obtain the vibration signal
Sample frequency, according to the sample frequency calculate median filter window width, be filtered according to the window width.
Preferably, the cloud is used to carry out median filtering to the vibration signal and wavelet-packet noise reduction is handled, specifically:
WAVELET PACKET DECOMPOSITION is carried out to the signal after median filtering, wavelet packet coefficient and best wavelet packet basis are determined, according to preset threshold value
The wavelet packet coefficient is handled, new wavelet packet coefficient is obtained, according to the new wavelet packet coefficient and the optimal wavelet
Packet base carries out signal reconstruction, the signal after obtaining noise reduction.
Preferably, the cloud is used to carry out cepstrum analysis to the signal after the noise reduction, obtains scramble spectrum signal, has
Body are as follows: the signal after the noise reduction is subjected to Fourier transformation, frequency spectral function is obtained, to the logarithm of the frequency spectral function
Inverse Fourier transform is carried out, scramble spectrum signal is obtained.
Preferably, the cloud is also used to be carried out according to operation trend of the scramble spectrum signal to the electromechanical equipment pre-
It surveys, the operation trend includes loss rank and remaining life.
By adopting the above technical scheme, it is combined using median filtering and wavelet-packet noise reduction, so that it is complicated to effectively eliminate mixing
While noise interferes vibration signal, the minutia of fault-signal is remained, by cepstrum analysis, sideband can be believed
It number separates, so that the periodic component for being difficult to differentiate in power spectrum is become discrete line spectrum in scramble spectrum signal, to have
Have the advantages of easily identification frequency variation, for it is uneven, misalign, the failures such as bearing's looseness, gear engagement can be very good
Identification, improves the accuracy of fault diagnosis.
Detailed description of the invention
Fig. 1 is electromechanical equipment sensor fixing structure schematic diagram provided in an embodiment of the present invention；
Fig. 2 is the flow chart of electromechanical equipment method for diagnosing faults provided in an embodiment of the present invention；
Fig. 3 is the cepstrum signal graph of electromechanical equipment imbalance fault provided in an embodiment of the present invention；
Fig. 4 is the cepstrum signal graph that electromechanical equipment provided in an embodiment of the present invention misaligns failure；
Fig. 5 is the cepstrum signal graph of electromechanical equipment bearing's looseness failure provided in an embodiment of the present invention；
Fig. 6 is the cepstrum signal graph of electromechanical equipment gear meshing fault provided in an embodiment of the present invention；
Fig. 7 is the position view of electromechanical equipment bearing fault provided in an embodiment of the present invention；
Fig. 8 is the structural block diagram of electromechanical equipment fault diagnosis system provided in an embodiment of the present invention.
Specific embodiment
Specific embodiments of the present invention will be further explained with reference to the accompanying drawing.It should be noted that for
The explanation of these embodiments is used to help understand the present invention, but and does not constitute a limitation of the invention.In addition, disclosed below
The each embodiment of the present invention involved in technical characteristic can be combined with each other as long as they do not conflict with each other.
Wherein, in the description of the embodiment of the present application, unless otherwise indicated, "/" indicate or the meaning, for example, A/B can be with
Indicate A or B；"and/or" herein is only a kind of incidence relation for describing affiliated partner, indicates that there may be three kinds of passes
System, for example, A and/or B, can indicate: individualism A exists simultaneously A and B, these three situations of individualism B.In addition, at this
In the description for applying for embodiment, " multiple " refer to two or more.
Hereinafter, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include one or more of the features.In the description of the embodiment of the present application, unless otherwise indicated, " multiples' " contains
Justice is two or more.
The electromechanical equipment method for diagnosing faults is applied in electromechanical equipment fault diagnosis system, functional failure of electromechanical diagnostic system
Including electromechanical equipment and cloud.Different measuring points are equipped with vibrating speed sensors and vibration on electromechanical equipment bearing vertical direction
Acceleration transducer, as shown in Figure 1, in figure 1 and 3 be bearing support；2 be main motor；4 be shaft coupling；5 be gear-box；6,8,
12,14,16,18 be vibration acceleration sensor；7,9,11,13,15,17,19 be communication controler；10 sense for vibration velocity
Device；20,21 be gear；22,23,24,25 be bearing.
As close to the supporting region of bearing when installation vibrating sensor, bearing is connected between sensor using rigidity
It connects, vibrating sensor and communication controler is installed in motor driven end bearing vertical direction, need to detect for different location
Signal behavior installs the vibrating speed sensors for degree of testing the speed and the vibration acceleration sensor of measuring acceleration, is passed by vibration velocity
Sensor and vibration acceleration sensor obtain the vibration velocity and acceleration information, that is, vibration signal of electromechanical equipment different location.
The collected vibration signal of vibrating sensor is transmitted to communication controler, the upper of data is realized by communication controler
It passes.Communication controler can be wireless module, such as wifi module, protenchyma networking module.
In a first aspect, as shown in Fig. 2, the embodiment of the invention provides a kind of electromechanical equipment method for diagnosing faults, electromechanics is set
Different measuring points are equipped with vibrating speed sensors and vibration acceleration sensor, vibrating speed sensors on standby bearing vertical direction
With vibration acceleration sensor for acquiring vibration signal, this method comprises:
Step S201, vibration signal is sent to cloud by electromechanical equipment；
Specifically, vibration signal is sent to by cloud by top communication controler.
Cloud herein can be server or host computer.
Step S202, cloud carries out median filtering to vibration signal and wavelet-packet noise reduction is handled, the signal after obtaining noise reduction；
Step S203, cloud carries out cepstrum analysis to the signal after noise reduction, obtains scramble spectrum signal；
Step S204, cloud carries out fault diagnosis according to scramble spectrum signal.
Because cepstrum signal intermediate frequency rate group component amount is different, event can be carried out according to the otherness of group of frequencies component amount
The positioning of barrier.
Cloud can be shown after diagnosing failure, to facilitate user to watch.
By adopting the above technical scheme, it is combined using median filtering and wavelet-packet noise reduction, so that it is complicated to effectively eliminate mixing
While noise interferes vibration signal, the minutia of fault-signal is remained, by cepstrum analysis, sideband can be believed
It number separates, so that the periodic component for being difficult to differentiate in power spectrum is become discrete line spectrum in scramble spectrum signal, to have
Have the advantages of easily identification frequency variation, for it is uneven, misalign, the failures such as bearing's looseness, gear engagement can be very good
Identification, improves the accuracy of fault diagnosis.
Preferably, in step S202: cloud carries out median filtering to vibration signal, specifically: obtain adopting for vibration signal
Sample frequency calculates the window width of median filter according to the sample frequency, is filtered according to the window width.
Specific steps are as follows:
1. obtaining the sample frequency Fs of up-delivering signal, the window width of median filter is calculated according to formula Ld=2LsFs
Ld。
2. after obtaining window width Ld, according to formula y (n)=Med [x (n-d) ..., x (n) ... x (n+d)] to noisy
Signal carries out median filtering.Set the discrete sampling sequence of signal x (t) wherein as x (n), Med [] expression takes all numbers in window
Median.
Preferably, in step S202: cloud carries out median filtering to vibration signal and wavelet-packet noise reduction is handled, specifically:
WAVELET PACKET DECOMPOSITION is carried out to the signal after median filtering, wavelet packet coefficient and best wavelet packet basis are determined, according to preset threshold value
The wavelet packet coefficient is handled, new wavelet packet coefficient is obtained, according to the new wavelet packet coefficient and the best wavelet packet basis into
Row signal reconstruction, the signal after obtaining noise reduction.
Specific steps are as follows:
(1) WAVELET PACKET DECOMPOSITION is carried out to the signal after median filtering, with formula
The cost function M (x) of expression determines optimal decomposition scale and wavelet packets as the judgment basis decomposed whether continuation
Base obtains wavelet packet coefficient.In formula: j indicates decomposition scale.
(2) preset threshold T is utilizedj,kEach wavelet packet coefficient W is handled with threshold function table expression formulaj,k, the new system that is estimated
NumberWherein
σj,kIt is poor for noise criteria, Wj,kFor the wavelet packet coefficient of k-th of subband of jth layer, N is signal length.
(3) pass through the new coefficient on each scale after threshold value is shunkAnd best wavelet packet basis, reconstruction signal obtain
Signal after to de-noising.
Preferably, in step S203: cloud carries out cepstrum analysis to the signal after noise reduction, obtains scramble spectrum signal, has
Body are as follows: the signal after noise reduction is subjected to Fourier transformation, obtains frequency spectral function, the logarithm of the frequency spectral function is carried out inverse
Fourier transformation obtains scramble spectrum signal.
Specifically: it obtained time-domain signal is first first carried out to Fourier transform is converted to frequency spectral function, then will obtain
Signal takes absolute value, then takes logarithm, carries out inverse Fourier transform after being carried out phase unwrapping, finally obtains cepstrum.
C=IFT (log (| FT (x (t)) |)+j2 π m)
Wherein m is real number, and x (t) is the time-domain signal received, the cepstrum that c is.
Preferably, it further comprises the steps of: cloud to be predicted according to operation trend of the scramble spectrum signal to electromechanical equipment, the fortune
Row trend includes loss rank and remaining life.To provide reference for relevant technical staff, help formulate equipment maintenance,
Maintenance plan.
Step S204, cloud carries out failure, diagnosis according to scramble spectrum signal specifically:
Different failures, which will lead to, there is corresponding amplitude in different frequencies.
1. illustrating what equipment occurred if detecting apparent fluctuation in a frequency multiplication of discovery motor speed on spectrogram
Failure problems are imbalances, as shown in Figure 3.
2. if all detecting apparent fluctuation, explanation in the frequency multiplication and two frequencys multiplication of discovery motor speed on spectrogram
The failure problems that equipment occurs are to misalign, as shown in Figure 4.
3. illustrating what equipment occurred if finding that motor turns all to detect vibration peak on the multiple frequence of frequency on spectrogram
The problem of failure is bearing's looseness, as shown in Figure 5.
4. if finding vibration peak occur near meshing frequency in motor mesh vibration waveform on spectrogram, and adjoint
Multiple turns frequency sideband, and the failure for illustrating that equipment occurs is hypodontia or meshing problem, as shown in Figure 6.
5. for bearing fault, if finding fault-signal frequency on frequency spectrum, the fault-signal frequency that receives with
The fault characteristic frequency being previously set is compared, so that it is determined that the happening part of bearing fault, as shown in Figure 7.Wherein: 71 are
Outer ring defect；72 be inner ring defect；73 be rolling volume defect；74 be retainer defect.
Specific failure-frequency:
For the various failures of bearing, there is corresponding accident analysis frequency.
Bearing retainer touches outer ring
Bearing retainer touches inner ring
Outer race failure
Bearing inner ring failure
Bearing roller single fault
Bearing roller Dual Failures
Transmission gear failure, oil seal ring touch mill f7=fn
D0 is the central diameter (rolling element pitch diameter) of bearing, mm；D is the diameter of rolling element, mm；Z is the quantity of rolling element；
Fn is the speed-frequency of the shaft where deagnostic package, for complicated transmission system, refers to axis where bearing, gear, tyre tread
Rotational frequency.
The present invention can be detected that electromechanical equipment is uneven by different frequency analyses, misaligned, lubricating oil analysis with
And the failure problems of gear engagement.Specific bearing fault position can also be determined by scramble spectrum signal, diagnostic result is very smart
Really.Relative to temperature diagnostic technology and the sightless failure of oil analyzing technology energy complete detection equipment naked eyes.Relative to using
Hand-held vibration gauge is utilized vibrating sensor and communication controler and reduces disappearing for manpower and material resources so that industrial equipment is intelligent
Consumption and the periodically workload of live inspection.For different fault conditions, long-range fault diagnosis is carried out using cloud computing, is supervised
The health status for surveying complication system, so that fault restoration much sooner, is much less unnecessary loss.
Second aspect, as shown in figure 8, the embodiment of the invention provides a kind of electromechanical equipment fault diagnosis system, including machine
Electric equipment 81 and cloud 82, different measuring points are equipped with vibrating speed sensors on electromechanical equipment bearing vertical direction and vibration accelerates
Sensor, vibrating speed sensors and vibration acceleration sensor are spent for acquiring vibration signal, which includes:
Electromechanical equipment 81 is used to vibration signal being sent to cloud 82；
Cloud 82 is used to carry out median filtering to vibration signal and wavelet-packet noise reduction is handled, the signal after obtaining noise reduction；
Cloud 82 is used to carry out cepstrum analysis to the signal after noise reduction, obtains scramble spectrum signal；
Cloud 82 is used to carry out fault diagnosis according to scramble spectrum signal.
Preferably, cloud is used to carry out median filtering to vibration signal specifically: obtains the sample frequency of vibration signal, root
The window width that median filter is calculated according to sample frequency, is filtered according to window width.
Preferably, cloud is used to carry out median filtering to vibration signal and wavelet-packet noise reduction is handled specifically: filters to intermediate value
Signal after wave carries out WAVELET PACKET DECOMPOSITION, wavelet packet coefficient and best wavelet packet basis is determined, according to preset threshold value to wavelet packet
Coefficient is handled, and new wavelet packet coefficient is obtained, and is carried out signal reconstruction according to new wavelet packet coefficient and best wavelet packet basis, is obtained
Signal after noise reduction.
Preferably, cloud is used to carry out cepstrum analysis to the signal after noise reduction, obtains scramble spectrum signal specifically: will drop
Signal after making an uproar carries out Fourier transformation, obtains frequency spectral function, carries out inverse Fourier transform to the logarithm of frequency spectral function,
Obtain scramble spectrum signal.
Preferably, cloud is also used to be predicted according to operation trend of the scramble spectrum signal to electromechanical equipment, operation trend
Including loss rank and remaining life.
In conjunction with attached drawing, the embodiments of the present invention are described in detail above, but the present invention is not limited to described implementations
Mode.For a person skilled in the art, in the case where not departing from the principle of the invention and spirit, to these embodiments
A variety of change, modification, replacement and modification are carried out, are still fallen in protection scope of the present invention.
Claims (10)
1. a kind of electromechanical equipment method for diagnosing faults, which is characterized in that different measuring points on the electromechanical equipment bearing vertical direction
Vibrating speed sensors and vibration acceleration sensor, the vibrating speed sensors and vibration acceleration sensing are installed
Device is used to acquire vibration signal, this method comprises:
The vibration signal is sent to cloud by the electromechanical equipment；
The cloud carries out median filtering to the vibration signal and wavelet-packet noise reduction is handled, the signal after obtaining noise reduction；
The cloud carries out cepstrum analysis to the signal after the noise reduction, obtains scramble spectrum signal；
The cloud carries out fault diagnosis according to the scramble spectrum signal.
2. electromechanical equipment method for diagnosing faults according to claim 1, which is characterized in that believe the vibration in the cloud
Number median filtering is carried out, specifically: the sample frequency for obtaining the signal calculates median filter according to the sample frequency
Window width is filtered according to the window width.
3. electromechanical equipment method for diagnosing faults according to claim 2, which is characterized in that believe the vibration in the cloud
Number carry out median filtering and wavelet-packet noise reduction processing, specifically: to after median filtering signal carry out WAVELET PACKET DECOMPOSITION, determine small
Wave packet coefficient and best wavelet packet basis handle the wavelet packet coefficient according to preset threshold value, obtain new wavelet packet system
Number carries out signal reconstruction according to the new wavelet packet coefficient and the best wavelet packet basis, the signal after obtaining noise reduction.
4. electromechanical equipment method for diagnosing faults according to claim 1, which is characterized in that after the cloud is to the noise reduction
Signal carry out cepstrum analysis, obtain scramble spectrum signal, specifically: by after the noise reduction signal carry out Fourier transformation,
Frequency spectral function is obtained, inverse Fourier transform is carried out to the logarithm of the frequency spectral function, obtains scramble spectrum signal.
5. electromechanical equipment method for diagnosing faults according to claim 1, which is characterized in that further comprise the steps of: the cloud
The operation trend of the electromechanical equipment is predicted according to the scramble spectrum signal, the operation trend include loss rank and
Remaining life.
6. a kind of electromechanical equipment fault diagnosis system, which is characterized in that including electromechanical equipment and cloud, the electromechanical equipment bearing
Different measuring points are equipped with vibrating speed sensors and vibration acceleration sensor on vertical direction, the vibrating speed sensors and
For acquiring vibration signal, which includes: the vibration acceleration sensor
The electromechanical equipment is used to the vibration signal being sent to cloud；
The cloud is used to carry out median filtering to the vibration signal and wavelet-packet noise reduction is handled, the signal after obtaining noise reduction；
The cloud is used to carry out cepstrum analysis to the signal after the noise reduction, obtains scramble spectrum signal；
The cloud is used to carry out fault diagnosis according to the scramble spectrum signal.
7. electromechanical equipment fault diagnosis system according to claim 6, which is characterized in that the cloud is used for the vibration
Dynamic signal carries out median filtering, specifically: the sample frequency for obtaining the vibration signal calculates intermediate value according to the sample frequency
The window width of filter is filtered according to the window width.
8. electromechanical equipment fault diagnosis system according to claim 7, which is characterized in that the cloud is used for the vibration
Dynamic signal carries out median filtering and wavelet-packet noise reduction processing, specifically: WAVELET PACKET DECOMPOSITION is carried out to the signal after median filtering, really
Determine wavelet packet coefficient and best wavelet packet basis, the wavelet packet coefficient is handled according to preset threshold value, obtains new small echo
Packet coefficient carries out signal reconstruction according to the new wavelet packet coefficient and the best wavelet packet basis, the signal after obtaining noise reduction.
9. electromechanical equipment fault diagnosis system according to claim 6, which is characterized in that the cloud is used for the drop
Signal after making an uproar carries out cepstrum analysis, obtains scramble spectrum signal, specifically: the signal after the noise reduction is subjected to Fourier's change
It changes, obtains frequency spectral function, inverse Fourier transform is carried out to the logarithm of the frequency spectral function, obtains scramble spectrum signal.
10. electromechanical equipment fault diagnosis system according to claim 6, which is characterized in that the cloud is also used to basis
The scramble spectrum signal predicts that the operation trend of the electromechanical equipment, the operation trend includes loss rank and residue
Service life.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910487476.5A CN110174281B (en) | 2019-06-05 | 2019-06-05 | Electromechanical equipment fault diagnosis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910487476.5A CN110174281B (en) | 2019-06-05 | 2019-06-05 | Electromechanical equipment fault diagnosis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110174281A true CN110174281A (en) | 2019-08-27 |
| CN110174281B CN110174281B (en) | 2021-08-13 |
Family
ID=67696973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910487476.5A Active CN110174281B (en) | 2019-06-05 | 2019-06-05 | Electromechanical equipment fault diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110174281B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110589021A (en) * | 2019-09-25 | 2019-12-20 | 东方航空技术有限公司 | Airplane anti-shake fault pre-judging system |
| CN110985425A (en) * | 2019-11-29 | 2020-04-10 | 联想(北京)有限公司 | Information detection method, electronic equipment and computer readable storage medium |
| CN112461356A (en) * | 2020-11-17 | 2021-03-09 | 南京同尔电子科技有限公司 | Test method for detecting oil seal abnormality in motor operation process through noise |
| CN117740370A (en) * | 2023-12-14 | 2024-03-22 | 广东派勒智能纳米科技股份有限公司 | Rotor fault diagnosis method, device, system and medium of nano sand mill |
| CN117874471A (en) * | 2024-03-11 | 2024-04-12 | 四川能投云电科技有限公司 | Water and electricity safety early warning and fault diagnosis method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1103951A2 (en) * | 1999-11-24 | 2001-05-30 | Matsushita Electric Industrial Co., Ltd. | Adaptive wavelet extraction for speech recognition |
| CN105181019A (en) * | 2015-09-15 | 2015-12-23 | 安徽精科检测技术有限公司 | Computer program product for early fault early-warning and analysis of rotation type machine |
| CN106855468A (en) * | 2015-12-09 | 2017-06-16 | 重庆市涪陵区德翔机电设备有限公司 | A kind of embedded electromechanical device state monitoring and fault diagnosis system |
| CN108550121A (en) * | 2018-03-30 | 2018-09-18 | 哈尔滨工程大学 | A kind of sediment sonar image processing method based on medium filtering and wavelet transformation |
| CN108613737A (en) * | 2018-05-14 | 2018-10-02 | 南京理工大学 | The discrimination method of aircraft multifrequency vibration signal based on wavelet packet and STFT |
| CN109029993A (en) * | 2018-06-20 | 2018-12-18 | 中国计量大学 | In conjunction with the bearing fault detection algorithm of genetic algorithm optimization parameter and machine vision |
| CN109708877A (en) * | 2018-12-27 | 2019-05-03 | 昆明理工大学 | Mechanical Failure Analysis method based on WAVELET FUZZY identification and image analysis theory |
| CN111272428A (en) * | 2020-02-17 | 2020-06-12 | 济南大学 | Rolling bearing fault diagnosis method based on improved Chebyshev distance |
-
2019
- 2019-06-05 CN CN201910487476.5A patent/CN110174281B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1103951A2 (en) * | 1999-11-24 | 2001-05-30 | Matsushita Electric Industrial Co., Ltd. | Adaptive wavelet extraction for speech recognition |
| CN105181019A (en) * | 2015-09-15 | 2015-12-23 | 安徽精科检测技术有限公司 | Computer program product for early fault early-warning and analysis of rotation type machine |
| CN106855468A (en) * | 2015-12-09 | 2017-06-16 | 重庆市涪陵区德翔机电设备有限公司 | A kind of embedded electromechanical device state monitoring and fault diagnosis system |
| CN108550121A (en) * | 2018-03-30 | 2018-09-18 | 哈尔滨工程大学 | A kind of sediment sonar image processing method based on medium filtering and wavelet transformation |
| CN108613737A (en) * | 2018-05-14 | 2018-10-02 | 南京理工大学 | The discrimination method of aircraft multifrequency vibration signal based on wavelet packet and STFT |
| CN109029993A (en) * | 2018-06-20 | 2018-12-18 | 中国计量大学 | In conjunction with the bearing fault detection algorithm of genetic algorithm optimization parameter and machine vision |
| CN109708877A (en) * | 2018-12-27 | 2019-05-03 | 昆明理工大学 | Mechanical Failure Analysis method based on WAVELET FUZZY identification and image analysis theory |
| CN111272428A (en) * | 2020-02-17 | 2020-06-12 | 济南大学 | Rolling bearing fault diagnosis method based on improved Chebyshev distance |
Non-Patent Citations (2)
| Title |
|---|
| 李方前等: "基于小波包——倒频谱的滚动轴承故障检测方法", 《电子技术与软件工程》 * |
| 高国伟等: "一种基于小波包变换和中值滤波的球团矿图像去噪方法", 《鞍山科技大学学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110589021A (en) * | 2019-09-25 | 2019-12-20 | 东方航空技术有限公司 | Airplane anti-shake fault pre-judging system |
| CN110985425A (en) * | 2019-11-29 | 2020-04-10 | 联想(北京)有限公司 | Information detection method, electronic equipment and computer readable storage medium |
| CN112461356A (en) * | 2020-11-17 | 2021-03-09 | 南京同尔电子科技有限公司 | Test method for detecting oil seal abnormality in motor operation process through noise |
| CN112461356B (en) * | 2020-11-17 | 2023-06-23 | 南京同尔电子科技有限公司 | Test method for detecting abnormal oil seal in motor operation process through noise |
| CN117740370A (en) * | 2023-12-14 | 2024-03-22 | 广东派勒智能纳米科技股份有限公司 | Rotor fault diagnosis method, device, system and medium of nano sand mill |
| CN117874471A (en) * | 2024-03-11 | 2024-04-12 | 四川能投云电科技有限公司 | Water and electricity safety early warning and fault diagnosis method and system |
| CN117874471B (en) * | 2024-03-11 | 2024-05-14 | 四川能投云电科技有限公司 | Water and electricity safety early warning and fault diagnosis method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110174281B (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110174281A (en) | A kind of electromechanical equipment fault diagnosis method and system | |
| Al-Balushi et al. | Gear fault diagnosis using energy-based features of acoustic emission signals | |
| CA2374748C (en) | Condition based monitoring of bearing by vibrational analysis | |
| EP3049788B1 (en) | Gear fault detection | |
| CN107976304B (en) | The mechanical disorder prediction analyzed based on the periodical information to signal | |
| CN103688144B (en) | A method and a system for analysing the condition of a rotating machine part | |
| CA2875071C (en) | Method and system for testing operational integrity of a drilling rig | |
| CN106197996A (en) | Offshore crane Fault Diagnosis of Gear Case device and method based on multivariate data | |
| CN203432784U (en) | State monitoring device used for rotary mechanical components | |
| CN110177017B (en) | Intelligent fault diagnosis system and diagnosis method for speed reducer | |
| EP3472579B1 (en) | Analysis of oversampled high frequency vibration signals | |
| Zhu et al. | Incipient fault diagnosis of roller bearings using empirical mode decomposition and correlation coefficient | |
| CN111060302A (en) | Multi-parameter equipment state comprehensive monitoring and diagnosing device and method | |
| Noman et al. | Oscillatory Lempel–Ziv complexity calculation as a nonlinear measure for continuous monitoring of bearing health | |
| KR20210006832A (en) | Method and apparatus for machine fault diagnosis | |
| CN112154314B (en) | Signal acquisition module for rotating mechanism, monitoring system, aircraft and method for monitoring rotating mechanism | |
| CN116252820A (en) | Polygonal quantitative detection method for high-speed train wheels driven by improved frequency domain integration method | |
| CN112901472B (en) | Diagnosis method for automatically identifying plunger pump fault based on signal characteristic frequency | |
| Thanagasundram et al. | Autoregressive based diagnostics scheme for detection of bearing faults | |
| Li et al. | Study on a novel fault diagnosis method of rolling bearing in motor | |
| Ogundare et al. | Review of fault detection techniques for health monitoring of helicopter gearbox | |
| CN207798428U (en) | Rotating machinery fault diagnosis system | |
| Mba et al. | Condition monitoring of low-speed rotating machinery using stress waves Part 2 | |
| Sikorska et al. | AE condition monitoring: challenges and opportunities | |
| CN211553263U (en) | Multi-parameter equipment state comprehensive monitoring and diagnosing device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |