CN114755010A - Rotary machine vibration fault diagnosis method and system - Google Patents

Rotary machine vibration fault diagnosis method and system Download PDF

Info

Publication number
CN114755010A
CN114755010A CN202210481208.4A CN202210481208A CN114755010A CN 114755010 A CN114755010 A CN 114755010A CN 202210481208 A CN202210481208 A CN 202210481208A CN 114755010 A CN114755010 A CN 114755010A
Authority
CN
China
Prior art keywords
vibration
rotary machine
data
scale
fault diagnosis
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.)
Pending
Application number
CN202210481208.4A
Other languages
Chinese (zh)
Inventor
李少华
李卓群
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zifisense Xiamen Co ltd
Original Assignee
Zifisense Xiamen Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zifisense Xiamen Co ltd filed Critical Zifisense Xiamen Co ltd
Priority to CN202210481208.4A priority Critical patent/CN114755010A/en
Publication of CN114755010A publication Critical patent/CN114755010A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M13/00—Testing of machine parts
    • G01M13/02—Gearings; Transmission mechanisms
    • G01M13/028—Acoustic or vibration analysis
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
    • G01H1/00—Measuring characteristics of vibrations in solids by using direct conduction to the detector
    • G01H1/003—Measuring characteristics of vibrations in solids by using direct conduction to the detector of rotating machines
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M13/00—Testing of machine parts
    • G01M13/02—Gearings; Transmission mechanisms

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)

Abstract

The application discloses a rotary machine vibration fault diagnosis method and a system thereof. The rotary machine vibration fault diagnosis method based on the trend-removing fluctuation analysis comprises the following steps of: acquiring vibration data of a rotating machine; constructing a time sequence matrix by using the vibration data, and processing the time sequence matrix to obtain a time domain signal matrix; determining a turning point of the average fluctuation function, and removing an analysis interval of the top fluctuation function according to the turning point; and determining a scale index according to a scale law relation on each scale interval, and performing fault diagnosis on the mechanical equipment by taking a vector formed by the scale indexes alpha as a feature vector. The method has the advantages that the fault characteristics of the equipment can be given, quantitative estimation can be carried out on the equipment, and the technical effect of accurate judgment of mechanical faults in qualitative and quantitative aspects is achieved.

Description

Rotary machine vibration fault diagnosis method and system
Technical Field
The application relates to the technical field of digital processing, in particular to a rotary machine vibration fault diagnosis method and system based on trend-removing fluctuation analysis.
Background
The vibration information of the device can reflect the operation state of the device. The existing equipment health state evaluation and fault diagnosis method mainly comprises a first type of fault diagnosis method based on signal analysis and processing technology, wherein the first type of fault diagnosis method comprises Fourier transformation, short-time Fourier transformation, wavelet transformation, empirical mode decomposition and the like. The second category of model-based mechanical fault diagnosis methods includes time series models, hidden markov models, co-factorial models, and the like. The third category of fault diagnosis methods based on big data and artificial intelligence includes neural networks, support vector machines, etc. The first and second fault diagnosis methods both require the system to be a steady linear system and extract characteristic values from the vibration signals, which can reflect the running state of the equipment, but the theoretical basis of the methods determines that the methods are only applicable to stable linear vibration signals; the third category of methods requires a large amount of historical data and high computational power to obtain reliable diagnostic results.
The working environment of mechanical equipment is usually complex, a plurality of vibration sources exist generally, and vibration signals obtained by measurement under the background of more interference signals mostly show non-stationarity, so that the three methods in practical engineering application show the defects of lack of simultaneous positioning function of time and frequency, limitation when processing non-stationary signals, limitation on resolution ratio and the like.
Based on the above analysis, it is necessary to establish a mechanical failure diagnosis method for a nonlinear system and suitable for edge storage and computational analysis.
Disclosure of Invention
The application provides a rotary machine vibration fault diagnosis method, which comprises the following steps:
step S1, obtaining vibration data of the rotary machine;
step S2, constructing a time sequence matrix by using the vibration data, and processing the time sequence matrix to obtain a time domain signal matrix;
step S3, performing detrending fluctuation analysis on each element in the time domain signal matrix to obtain a fluctuation function of each element in the time sequence matrix, and averaging the fluctuation functions in each direction in the time sequence matrix to obtain an average fluctuation function;
step S4, determining the turning point of the average fluctuation function by logarithmic coordinates, determining the scale interval of the fluctuation function according to the turning point, and determining the scale index according to the scale law relationship on each scale interval;
In step S5, a rotary machine vibration failure diagnosis is performed using the vector constituted by the scale index as a feature vector.
The method and the system for diagnosing the vibration fault of the rotary machine have the advantages that the rotary machine which needs to be subjected to fault diagnosis is subjected to data acquisition through the sensor, vibration data are obtained, and the data are uploaded to the processor; wherein the vibration data includes vibration signals from three directions of the rotary machine.
The method for diagnosing a vibration fault of a rotating machine as described above, wherein step S2 specifically includes the following sub-steps:
constructing a time sequence matrix by using the vibration data;
segmenting the time sequence matrix to obtain time subsequence matrixes in all directions;
and forming a time domain signal matrix by using the time subsequence matrixes in all directions.
The method and the system for diagnosing the vibration fault of the rotary machine utilize the window function to the time sequence matrix Xi,jAnd (t) dividing any one-dimensional variable to obtain k subsequences under the time scale tau.
The method for diagnosing a vibration fault of a rotating machine as described above, wherein the step S3 specifically includes the following sub-steps:
constructing a mean value-removed cumulative summation sequence;
Dividing the cumulative summation sequence equally according to the length n;
each segment of data is fitted in a segmented manner
Figure BDA0003627944080000031
Polynomial trend of Ln(i)；
According to a polynomial trend Ln(i) And subsegments of cumulative sum sequences
Figure BDA0003627944080000032
Calculating a root mean square fluctuation function of the time series;
and changing the size of the dimension n and repeating the steps.
The method for diagnosing the vibration fault of the rotary machine is characterized in that a least square method is adopted to fit a polynomial trend of each section of data.
A method for diagnosing vibration failure of rotary machine as described above, wherein, for each sub-sequence of the cumulative summation sequence, the sub-segments of the cumulative summation sequence are calculated according to the root mean square fluctuation function calculation formula
Figure BDA0003627944080000033
Root mean square fluctuation function of.
In the method for diagnosing the vibration fault of the rotary machine, logarithms are taken at two ends of the average fluctuation function at the same time, gradient values of the discrete function at different points are obtained, and the scale of the fluctuation function is determined by taking the standard that the change percentage of the gradient values is larger than the average gradient.
The invention also provides a rotary machine vibration fault diagnosis system based on trend-removing fluctuation analysis, which comprises: a rotating machine, a sensor, and a processor;
wherein the sensor: the vibration data acquisition module is used for acquiring vibration data of the rotary machine and uploading the acquired vibration data to the processor for processing; the vibration data includes vibration signals from three directions of the rotary machine;
The processor: the rotary machine vibration fault diagnosis method is used for receiving the vibration data, executing any one of the above methods based on the detrending fluctuation analysis, processing the data and obtaining a diagnosis result.
By adopting the rotary machine vibration fault diagnosis method and system based on trend-removing fluctuation analysis, weak or unstable fault characteristic signals generated by vibration equipment can be processed, the rotary machine vibration fault diagnosis method and system can be suitable for different fields such as different sampling moments, sample sizes and sampling frequencies, the fault characteristics of the equipment are given, and the technical effect of accurate judgment of mechanical faults in both qualitative and quantitative aspects is achieved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the description below are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art according to these drawings.
FIG. 1 is a flow chart of a rotary machine vibration fault diagnosis method based on detrended fluctuation analysis;
FIG. 2 is a calibration curve of one embodiment of a rotary machine vibration fault diagnostic method based on detrended fluctuation analysis.
FIG. 3 is a different fault scale plot of another embodiment of a rotary machine vibration fault diagnostic method based on detrended fluctuation analysis.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
The application provides a rotary machine vibration fault diagnosis method and system based on trend-removing fluctuation analysis, which can process weak or unstable fault characteristic signals generated by vibration equipment, can be suitable for different fields such as different sampling moments, sample sizes and sampling frequencies, not only can give fault characteristics of the equipment, but also can quantitatively estimate the fault characteristics, and can also realize accurate judgment of mechanical faults in qualitative and quantitative aspects.
The application provides a rotating machinery fault diagnosis system based on remove trend fluctuation analysis, includes: a rotating machine, a sensor, and a processor;
wherein the sensor: the vibration data acquisition module is used for acquiring vibration data of the rotary machine and uploading the acquired vibration data to the processor for processing; the vibration data includes vibration signals from three directions of the rotary machine.
A processor: the system is used for receiving vibration data uploaded by the sensor and executing a rotary machine vibration fault diagnosis method based on trend-removing fluctuation analysis, and processing the vibration data to obtain a diagnosis result.
To achieve the above object, as shown in fig. 1, the present application provides a method for diagnosing a fault of a rotating machine based on detrending fluctuation analysis, comprising the steps of:
step S1: vibration data of the rotating machine is acquired.
Specifically, a sensor is used for acquiring data of the rotary machine which needs fault diagnosis, vibration data are obtained, and the data are uploaded to a processor. Wherein the vibration data includes vibration signals from three directions of the rotary machine.
Step S2: constructing a time sequence matrix by using the vibration data, and processing the time sequence matrix to obtain a time domain signal matrix;
In the embodiment of the present application, the constructed time series matrix may be any dimension matrix, such as a three-dimensional time series matrix, but is not limited to the three-dimensional time series matrix.
Specifically, step S2 specifically includes the following sub-steps:
s21: a time series matrix is constructed using the vibration data.
Specifically, after the processor receives vibration data uploaded by the sensor, a one-dimensional variable is constructed by using vibration signals in each direction in the vibration data, and a three-dimensional time sequence matrix is constructed by using all the constructed one-dimensional variables.
Specifically, taking the three-dimensional time series matrix as an example, the expression of the three-dimensional time series matrix is as follows:
Figure BDA0003627944080000051
wherein Xi,j(t) is a three-dimensional time series matrix; i denotes the direction of the sensor measurement and ranges from i h, v, s, where i h denotes the horizontal direction d of the rotating machinehI-v denotes a rotary machineTangential direction d of the machinevAnd i-s denotes an axial direction d of the rotary machines(ii) a N is a positive integer and represents the total sampling times; j represents any one sample data; t denotes a time domain.
S22: and (4) segmenting the time sequence matrix to obtain time subsequence matrixes in all directions.
Specifically, a three-dimensional time series matrix X is formed by using a window function i,j(t) any dimension variable is segmented to obtain k subsequences under the time scale tau, wherein the specific expression of the rectangular window function is as follows:
Figure BDA0003627944080000061
wherein, Wu(l) The vector is an arbitrary rectangular window function, u is an index of a subsequence, is a natural number, and has a value range of u being 1,2,3,. eta., k; τ is a time scale; k is the number of subsequences; l is [0, N]Is a natural number of (1).
Specifically, the specific expression of the subsequence matrix is as follows:
Figure BDA0003627944080000062
wherein, ym(t)Is an expression of a subsequence matrix;
Figure BDA0003627944080000063
represents an arbitrary subsequence;
Figure BDA0003627944080000064
is a subsequence when u ═ k; m is a direction number of the vibration signal, and m is 1,2,3, where m h represents a horizontal direction d of the rotary machinehThe vibration signal of (a); where m-v denotes the tangential direction d of the rotating machinevM-s represents the axial direction d of the rotating machinesThe vibration signal of (a); k is the number of subsequences; t denotes a time domain.
Wherein the expression of any subsequence is as follows:
Figure BDA0003627944080000065
wherein x ism,(u-1)τ+nIs any element in any subsequence; x is the number ofm,uτAn element where n is τ; n is a natural number, and the value range of n is 1,2, 3.
S23: and forming a time domain signal matrix by using the time subsequence matrixes in all directions.
Repeating the substep S22 to obtain time subsequence matrixes in all directions, and forming a time domain signal matrix by using the time subsequence matrixes in all directions, wherein the specific expression is as follows:
Figure BDA0003627944080000066
Wherein, Y (t) is a time domain signal matrix; t represents a time domain; u is the index of the subsequence and has a value range of u being 1,2, 3. k is the number of subsequences.
Step S3: performing detrending fluctuation analysis on each element in the time domain signal matrix;
specifically, step S3 includes the following sub-steps:
s31: a de-averaged cumulative summation sequence is constructed.
Specifically, a cumulative summation sequence of each element in the time domain signal matrix is calculated according to a cumulative summation formula of the mean value removal.
Figure BDA0003627944080000071
The mean value of each element in the time domain signal matrix Y (t) is respectively calculated by using the expression for obtaining the mean value, so as to obtain the mean value of each element in the time domain signal matrix. The expression for obtaining the mean is as follows:
Figure BDA0003627944080000072
wherein x (i) is the vibration signal amplitude; n is the number of the time domain signals of the segment, and i is the sequence index of the vibration signal.
S32: the cumulative summation sequence is divided equally by length n, each segment of the cumulative summation sequence is represented as
Figure BDA0003627944080000073
Wherein K is 1, 2.., K; 1, 2.
Specifically, the sequence is divided into K equal parts according to the length N of the sequence, the length of each part of data is N, and each part is expressed as
Figure BDA0003627944080000074
S33: respectively fitting each segment of data by adopting a least square method
Figure BDA0003627944080000075
Polynomial trend of L n(i)。
Specifically, assuming that the order of the fitted polynomial is m, the expression of the polynomial is:
Figure BDA0003627944080000076
determining each coefficient a in the equation according to the least square methodqSize and calculate data according to the following formula
Figure BDA0003627944080000077
Corresponding polynomial trend Ln(i)：
Figure BDA0003627944080000078
S34: according to a polynomial trend Ln(i) And subsegments of cumulative sum sequences
Figure BDA0003627944080000079
Calculating the root mean square fluctuation function of the time series:
specifically, for each subsequence of the cumulative summation sequence, the subsequences of the cumulative summation sequence are calculated according to a root mean square fluctuation function calculation formula
Figure BDA0003627944080000081
Root mean square fluctuation function f (n);
the root mean square fluctuation function calculation formula is as follows:
Figure BDA0003627944080000082
s35: the size of the scale n is changed, and the steps S32 to S34 are repeated.
Specifically, n varies from 20,21,23,., repeating the steps S32 to S34, so as to obtain the F (n) size under different n values.
Referring back to fig. 1, step S4: repeating the step S3, and performing detrending fluctuation analysis on each element in the time sequence matrix to obtain a fluctuation function F of each element in the time sequence matrixk(n)；
Step S5: for a ripple function F in each direction in the time-series matrixk(n) averaging to obtain an average fluctuation function:
specifically, according to an average fluctuation function calculation formula, an average fluctuation function in each direction is calculated:
Figure BDA0003627944080000083
Step S6: and determining the turning point of the average fluctuation function by using the logarithmic coordinate, and determining the analysis interval of the fluctuation function according to the turning point.
Specifically, logarithms are taken at two ends of the average fluctuation function at the same time, gradient values of the discrete function at different points are solved, and the scale of the fluctuation function is determined by taking the standard that the change percentage of the gradient values is larger than the average gradient.
Step S7: over each scale interval, a scale index α is determined according to a scale law relationship.
In particular, the mean fluctuation function
Figure BDA0003627944080000084
And the scale rule relation exists in a certain interval range of the scale n:
Figure BDA0003627944080000085
calculating a scale index α from the relational expression (12) in combination with the scale section determined in step S6;
s8: and (4) taking a vector formed by the scale indexes alpha as a characteristic vector to carry out fault diagnosis on the mechanical equipment.
Specifically, the scale index α is used as a feature vector, and whether the mechanical equipment fails or not is judged according to the change between euclidean distances of the feature vector in different states or other linear classification methods.
The method has the advantages that weak or non-stable fault characteristic signals generated by the vibration equipment can be processed, the method can be suitable for different fields such as different sampling moments, sample sizes and sampling frequencies, not only can the fault characteristics of the equipment be given, but also the fault characteristics can be quantitatively estimated, and the technical effect of accurate judgment of mechanical faults in qualitative and quantitative aspects is achieved.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, the scope of protection of this application is intended to be construed as including the preferred embodiments and all variations and modifications that fall within the scope of the application. It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims (9)

1. A rotary machine vibration failure diagnosis method, characterized by comprising:
step S1, obtaining vibration data of the rotating machine;
step S2, constructing a time sequence matrix by using the vibration data, and processing the time sequence matrix to obtain a time domain signal matrix;
step S3, performing detrending fluctuation analysis on each element in the time domain signal matrix to obtain a fluctuation function of each element in the time sequence matrix, and averaging the fluctuation functions in each direction in the time sequence matrix to obtain an average fluctuation function;
Step S4, determining the turning point of the average fluctuation function by using the logarithmic coordinate, determining the scale interval of the fluctuation function according to the turning point, and determining the scale index according to the scale law relation in each scale interval;
in step S5, a rotary machine vibration failure diagnosis is performed using the vector constituted by the scale index as a feature vector.
2. A vibration fault diagnosis method for a rotary machine according to claim 1, wherein a sensor acquires data of the rotary machine to be subjected to fault diagnosis, obtains vibration data, and uploads the data to a processor; wherein the vibration data includes vibration signals from three directions of the rotary machine.
3. A method for diagnosing a vibration failure of a rotary machine as claimed in claim 1, wherein the step S2 specifically includes the sub-steps of:
constructing a time sequence matrix by using the vibration data;
segmenting the time sequence matrix to obtain time subsequence matrixes in all directions;
and forming a time domain signal matrix by using the time subsequence matrixes in all directions.
4. A rotary machine as claimed in claim 3The vibration fault diagnosis method is characterized in that a window function-time sequence matrix X is utilized i,jAnd (t) dividing any one-dimensional variable to obtain k subsequences under the time scale tau.
5. A method for diagnosing a vibration failure of a rotary machine as claimed in claim 1, wherein the step S3 specifically includes the sub-steps of:
constructing a mean-removed cumulative summation sequence;
equally dividing the cumulative summation sequence according to the length n;
each segment of data is fitted in a segmented manner
Figure FDA0003627944070000021
Polynomial trend of (L)n(i)；
According to a polynomial trend Ln(i) And subsegments of cumulative sum sequences
Figure FDA0003627944070000022
Calculating a root mean square fluctuation function of the time series;
and changing the size of the dimension n, and repeating the steps.
6. A rotary machine vibration failure diagnosis method according to claim 5, wherein a least square method is adopted to fit a polynomial trend of each segment of data.
7. A method according to claim 5, characterized in that for each subsequence of the cumulative sum sequence, the calculation of subsections of the cumulative sum sequence is performed according to a root mean square ripple function calculation formula
Figure FDA0003627944070000023
Root mean square ripple function of (c).
8. A method of diagnosing a vibration fault in a rotary machine according to claim 1, wherein the mean fluctuation function is logarithmized simultaneously at both ends, and the gradient values of the discrete function at different points are evaluated, and the scale of the fluctuation function is determined on the basis that the percentage change of the gradient values is larger than the mean gradient.
9. A rotary machine vibration fault diagnosis system based on detrended fluctuation analysis, comprising: a rotating machine, a sensor, and a processor;
wherein the sensor: the vibration data acquisition module is used for acquiring vibration data of the rotary machine and uploading the acquired vibration data to the processor for processing; the vibration data includes vibration signals from three directions of the rotary machine;
the processor: the rotary machine vibration fault diagnosis method is used for receiving the vibration data and executing the rotary machine vibration fault diagnosis method based on the detrended fluctuation analysis of any one of claims 1-8, and processing the data to obtain a diagnosis result.
CN202210481208.4A 2022-05-05 2022-05-05 Rotary machine vibration fault diagnosis method and system Pending CN114755010A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210481208.4A CN114755010A (en) 2022-05-05 2022-05-05 Rotary machine vibration fault diagnosis method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210481208.4A CN114755010A (en) 2022-05-05 2022-05-05 Rotary machine vibration fault diagnosis method and system

Publications (1)

Publication Number Publication Date
CN114755010A true CN114755010A (en) 2022-07-15

Family

ID=82333506

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210481208.4A Pending CN114755010A (en) 2022-05-05 2022-05-05 Rotary machine vibration fault diagnosis method and system

Country Status (1)

Country Link
CN (1) CN114755010A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN117906946A (en) * 2024-03-20 2024-04-19 江苏金恒信息科技股份有限公司 Gear fault alarm method based on multi-scale peak searching

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN117906946A (en) * 2024-03-20 2024-04-19 江苏金恒信息科技股份有限公司 Gear fault alarm method based on multi-scale peak searching
CN117906946B (en) * 2024-03-20 2024-05-31 江苏金恒信息科技股份有限公司 Gear fault alarm method based on multi-scale peak searching

Similar Documents

Publication Publication Date Title
CN114755010A (en) Rotary machine vibration fault diagnosis method and system
CN111767930A (en) Method for detecting abnormal time series data of Internet of things and related equipment thereof
CN111307438B (en) Rotary machine vibration fault diagnosis method and system based on information entropy
CN112633098B (en) Rotary machine fault diagnosis method, system and storage medium
JP7126256B2 (en) Abnormality diagnosis device, abnormality diagnosis method, and program
Montechiesi et al. Artificial immune system via Euclidean Distance Minimization for anomaly detection in bearings
CN112416662A (en) Multi-time series data anomaly detection method and device
CN112179653A (en) Rolling bearing vibration signal blind source separation method and device and computer equipment
CN115127806A (en) Gear box fault diagnosis method and device based on multi-sensor vibration signals
CN117633696A (en) Hydraulic engineering construction monitoring method and system based on BIM model
CN117251798A (en) Meteorological equipment anomaly detection method based on two-layer progressive process
Meng et al. A gear fault diagnosis method based on improved accommodative random weighting algorithm and BB-1D-TP
CN117093947B (en) Power generation diesel engine operation abnormity monitoring method and system
CN116776245A (en) Three-phase inverter equipment fault diagnosis method based on machine learning
CN116595465A (en) High-dimensional sparse data outlier detection method and system based on self-encoder and data enhancement
CN110990383A (en) Similarity calculation method based on industrial big data set
CN114021275B (en) Rolling bearing fault diagnosis method based on deep convolution fuzzy system
CN114970624A (en) Asynchronous fault diagnosis system and method for double-motor driven ratchet-pawl speed reducer
CN114993671A (en) Vibration fault diagnosis method and system based on Q factor wavelet transform
CN115236272A (en) Gas sensor fault diagnosis method and device under multi-working condition and storage medium
CN115291103A (en) Motor fault diagnosis method based on GR-SWPT wavelet packet algorithm embedded with HD-RCF
CN113420710A (en) Sensor data noise reduction method based on multi-resolution wavelet
CN115758094B (en) Method for extracting degradation index and predicting service life of speed reducer
CN113642407B (en) Feature extraction optimization method suitable for predicting residual service life of bearing
CN117949821B (en) Asynchronous motor fault diagnosis method and related equipment

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