CN112985809A - Rolling bearing fault diagnosis method based on signal multi-dimensional fine image - Google Patents
Rolling bearing fault diagnosis method based on signal multi-dimensional fine image Download PDFInfo
- Publication number
- CN112985809A CN112985809A CN202110178425.1A CN202110178425A CN112985809A CN 112985809 A CN112985809 A CN 112985809A CN 202110178425 A CN202110178425 A CN 202110178425A CN 112985809 A CN112985809 A CN 112985809A
- Authority
- CN
- China
- Prior art keywords
- fault
- rolling bearing
- signal
- entropy
- features
- 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
Links
- 238000005096 rolling process Methods 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000003745 diagnosis Methods 0.000 title claims abstract description 15
- 238000000605 extraction Methods 0.000 claims abstract description 45
- 230000036541 health Effects 0.000 claims abstract description 9
- 230000003595 spectral effect Effects 0.000 claims abstract description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 16
- 239000002131 composite material Substances 0.000 claims description 11
- 238000001228 spectrum Methods 0.000 claims description 11
- 230000000877 morphologic effect Effects 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003862 health status Effects 0.000 description 2
- 230000001131 transforming effect Effects 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
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
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
Abstract
The invention provides a rolling bearing fault diagnosis method based on signal multi-dimensional fine image, comprising the following steps: s1: denoising the acquired fault signals by using lifting wavelets; s2: performing feature extraction in a time domain to obtain signal health state features; s3: performing feature extraction to obtain spectral features; s4: performing feature extraction to obtain entropy features; s5: performing feature extraction to obtain multi-fractal dimension features; s6: establishing a fine picture about the rolling bearing fault; s7: and determining the occurrence position of the rolling bearing fault. According to the rolling bearing fault diagnosis method based on the signal multi-dimensional fine image, the fault characteristics are extracted from different angles by adopting various methods to establish the fine image of the rolling bearing fault, and the fault characteristics extracted from multiple angles are fused to show the complete rolling bearing fault characteristics, so that the fault occurrence position is accurately diagnosed.
Description
Technical Field
The invention relates to the field of fault diagnosis of rolling bearings, in particular to a fault diagnosis method of a rolling bearing based on multi-dimensional fine image of signals.
Background
At present, the main technology for extracting the fault characteristics of the rolling bearing firstly uses a denoising technology to perform denoising processing on acquired data, such as: wavelet threshold, spatial correlation, Butterworth band-pass filter and the like, and the methods can remove noise of the fault signals of the rolling bearing to a certain extent by selecting proper parameter values. And then, carrying out corresponding feature extraction on the denoised rolling bearing fault signal by adopting different feature extraction methods. Such as: the method comprises Maximum Correlation Kurtosis Deconvolution (MCKD) and an envelope spectrum, composite multi-scale dispersion entropy and the like, wherein the Maximum Correlation Kurtosis Deconvolution (MCKD) and the envelope spectrum are improved on the basis of minimum entropy deconvolution and are used for feature extraction of weak fault signals, and the composite multi-scale dispersion entropy solves the problems of inaccurate entropy value, large fluctuation and the like of multi-scale entropy.
Although the wavelet threshold, the spatial correlation, the Butterworth band-pass filter and other methods can achieve denoising with a certain effect by selecting appropriate parameters, the parameters need to be manually set, the most appropriate parameters are difficult to select, a hard threshold function can generate singular points when the wavelet threshold is used for denoising, the soft threshold function is continuous in a wavelet domain, a coefficient of wavelet estimation of the soft threshold function is different from an actual value by a threshold t, namely, a certain deviation exists in a signal, the spatial correlation is difficult to set and process a threshold of a correlation coefficient, and the Butterworth band-pass filter can generate the problems of deviation, distortion and the like when the Butterworth band-pass filter denoises the signal. Although feature extraction can be performed under weak fault signals for maximum correlation kurtosis deconvolution and envelope spectrums, knowledge of fault period setting is required to be possessed in advance, and time cost is increased during filter design. Although the composite multi-scale spreading entropy improves the problems of inaccurate entropy value and large fluctuation of multi-scale entropy, the problem of undefined entropy caused by too short time sequence of samples cannot be solved.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a rolling bearing fault diagnosis method based on a signal multi-dimensional fine image.
In order to achieve the above object, the present invention provides a rolling bearing fault diagnosis method based on signal multi-dimensional fine image, comprising the steps of:
s1: denoising the collected fault signal of a rolling bearing by using lifting wavelets;
s2: carrying out feature extraction in a time domain on the denoised fault signal to obtain signal health state features;
s3: carrying out feature extraction on the denoised fault signal to obtain a spectrum feature;
s4: carrying out feature extraction on the denoised fault signal to obtain entropy features;
s5: carrying out feature extraction on the denoised fault signal to obtain a multi-fractal dimension feature;
s6: establishing a fine sketch of the rolling bearing fault using the signal state of health feature, the spectral feature, the entropy feature, and the multi-fractal dimension feature;
s7: and determining the occurrence position of the rolling bearing fault by using the fine image of the rolling bearing fault.
Preferably, the signal health status features comprise dimensionless features including a peak factor, a pulse factor, a margin factor, and a kurtosis factor.
Preferably, the spectral characteristics include a fault characteristic of a low-speed rolling bearing and an early fault characteristic of a rolling bearing; the S3 further includes the steps of:
s31: adopting a stress wave method of continuous wavelet analysis, establishing a mechanical model of the rolling bearing by using a finite element numerical analysis method, and extracting fault characteristics of the low-speed rolling bearing by extracting signal fault characteristic frequency from a reconstructed waveform after multi-scale decomposition and reconstruction processing are carried out on a stress wave signal;
s32: and performing feature extraction on the denoised fault signal of the rolling bearing by adopting multipoint optimal minimum entropy deconvolution correction and a square envelope spectrum, and extracting early fault features of the rolling bearing.
Preferably, the entropy features comprise EMD entropy features and fine composite multi-scale entropy features, and the EMD entropy features comprise EMD singular entropy and EMD sample entropy;
the step of S4 further includes the steps of:
s41: decomposing the fault signal after the rolling bearing is denoised by using an EMD method;
s42: respectively calculating the EMD singular entropy of the IMF and the EMD sample entropy and fusing to obtain the EMD entropy characteristics;
s43: and extracting the fine composite multi-scale entropy characteristics.
Preferably, the step S42 is followed by a step of performing dimension reduction fusion on the EMD entropy features by using a KPCA feature extraction method.
Preferably, the multi-fractal dimension characteristic includes a first fault characteristic and a second fault characteristic; the step of S5 further includes the steps of:
s51: performing feature extraction on the denoised fault signal of the rolling bearing by adopting local feature scale decomposition and morphological fractal dimension to obtain a first fault feature;
s52: performing feature extraction on the denoised fault signal of the rolling bearing by adopting variational modal decomposition and generalized fractal dimension to obtain a second fault feature;
s53: combining the first fault signature and the second fault signature to form the multi-fractal dimension signature.
Due to the adoption of the technical scheme, the invention has the following beneficial effects:
the fine portrait of the fault characteristics of the rolling bearing respectively adopts a plurality of different methods to extract the characteristics of the signals from the aspects of time domain, frequency domain and the like of the signals, and the phenomenon that the finally extracted fault characteristics are lacked due to different adaptive ranges of a certain extraction mode is effectively overcome due to the adoption of the plurality of different methods to extract the characteristics of the signals, so that the complete fault characteristics can not be extracted. Meanwhile, the fine portrait of the fault characteristics can provide the diagnostic personnel with the characteristic extraction effect of the same fault signal in different aspects, so that the diagnostic personnel can more accurately analyze and judge the fault position and take effective measures to solve the fault, and the fault solving efficiency is improved.
Drawings
Fig. 1 is a flowchart of a rolling bearing fault diagnosis method based on signal multi-dimensional fine imaging according to an embodiment of the present invention.
Detailed Description
The following description of the preferred embodiment of the present invention, in accordance with the accompanying drawings of which 1 is presented to enable a better understanding of the invention as to its functions and features.
Referring to fig. 1, a rolling bearing fault diagnosis method based on a multi-dimensional fine image of a signal according to an embodiment of the present invention includes:
s1: denoising the collected fault signal of a rolling bearing by using lifting wavelets;
the lifting wavelet abandons the limitation that the traditional wavelet uses a mother function of expansion and translation to form a wavelet base, so the lifting wavelet can analyze the problem in a frequency domain without using the traditional Fourier transform as a main analysis tool, thereby transforming the problem into a time domain for transformation, and transforming a high-pass filter and a low-pass filter into a series of prediction and updating steps. Therefore, the lifting wavelet can achieve better effect in signal denoising compared with other wavelet transformation.
S2: carrying out feature extraction in a time domain on the denoised fault signal to obtain signal health state features;
the signal health status features include dimensionless features including a peak factor, a pulse factor, a margin factor, and a kurtosis factor.
The size of the dimensional characteristic value can be changed correspondingly according to different adopted data, the change of the working environment can also have great influence on the dimensional characteristic value, and the dimensionless characteristic is not sensitive to the transformation of external factors and basically cannot be influenced by the rotating speed, the load and the like. Therefore, dimensionless characteristic peak value factors and pulse factors are adopted to detect whether the signals have indexes of impact or not, margin factors are adopted to detect the abrasion condition of mechanical equipment, and the kurtosis factors reflect the impact characteristics of the vibration signals, so that the health state of the signals is represented.
S3: carrying out feature extraction on the denoised fault signal to obtain a spectrum feature;
the spectrum characteristics comprise fault characteristics of a low-rotating-speed rolling bearing and early fault characteristics of the rolling bearing; the S3 further includes the steps of:
s31: adopting a stress wave method of continuous wavelet analysis, establishing a mechanical model of the rolling bearing by using a finite element numerical analysis method, and extracting fault characteristics of the low-speed rolling bearing by extracting signal fault characteristic frequency from a reconstructed waveform after multi-scale decomposition and reconstruction processing are carried out on a stress wave signal;
s32: and performing feature extraction on the denoised fault signal of the rolling bearing by adopting multipoint optimal minimum entropy deconvolution correction and a square envelope spectrum, and extracting early fault features of the rolling bearing.
The two methods are combined to completely describe the characteristic conditions of the fault under different times and states such as low rotating speed, high rotating speed, early fault and the like.
S4: carrying out feature extraction on the denoised fault signal to obtain entropy features;
the entropy features comprise EMD entropy features and fine composite multi-scale entropy features, and the EMD entropy features comprise EMD singular entropy and EMD sample entropy;
the step of S4 further includes the steps of:
s41: decomposing the fault signal after the rolling bearing is denoised by using an EMD method;
s42: respectively calculating the EMD singular entropy of the IMF and the EMD sample entropy and fusing to obtain the EMD entropy characteristics; realizing complementation among entropy characteristics to obtain fault characteristics richer than using a certain entropy;
s43: and extracting the fine composite multi-scale entropy characteristics.
Preferably, the step S42 is followed by a step of performing dimension reduction fusion on the EMD entropy features by using a KPCA feature extraction method. Because the EMD entropy characteristics are overlapped sometimes, the KPCA characteristic extraction method is adopted to perform dimensionality reduction fusion on the EMD entropy characteristics so that the fault characteristics are well separated, the discrimination and the clustering are improved, and the fault characteristics are better represented.
And EMD entropy feature fusion is adopted to extract the fault features of the rolling bearing, and the time-frequency features of signals can be simultaneously, accurately and completely extracted without any entropy feature. The EMD singular entropy can describe the complexity and the uncertainty of the distribution of the signal in a frequency-variable space, the EMD sample entropy can describe the energy distribution and the complexity of the signal in a time-variable space, two entropy characteristics are fused to serve as fault characteristics, and the complementarity of a fault characteristic space and the fault characteristic extraction rate are effectively improved.
And the fine composite multi-scale entropy features are used for carrying out feature extraction on the rolling bearing fault signals with short extracted sample time, so that the probability of inducing undefined entropy is reduced, and the fault features of the rolling bearing are extracted more accurately.
S5: carrying out feature extraction on the denoised fault signal to obtain a multi-fractal dimension feature;
the multi-fractal dimension features include a first fault feature and a second fault feature; the step of S5 further includes the steps of:
s51: performing feature extraction on the denoised fault signal of the rolling bearing by adopting local feature scale decomposition and morphological fractal dimension to obtain a first fault feature;
s52: performing feature extraction on the denoised fault signal of the rolling bearing by adopting variational modal decomposition and generalized fractal dimension to obtain a second fault feature;
s53: combining the first fault signature and the second fault signature to form the multi-fractal dimension signature.
The rolling bearing fault signal is subjected to feature extraction by adopting local feature scale decomposition and morphological fractal dimension, and as the mathematical morphological fractal dimension is sensitive to noise, noise reduction processing is required to be carried out to obtain accurate fractal dimension from the acquired signal, but a traditional linear filter is generally not good enough. Therefore, local characteristic scale decomposition is adopted for denoising, and the method can decompose the vibration signal into a single rotation component with the physical significance of the instantaneous frequency. And calculating the mathematical morphological fractal dimension of each rotation component, and taking the mathematical morphological fractal dimension as the fault characteristic of the rolling bearing. And then, performing feature extraction on the rolling bearing fault signal again by adopting variational modal decomposition and generalized fractal dimension, determining the frequency center and bandwidth of each component by iteratively searching the optimal solution of the variational model to obtain a decomposition component, so as to decompose the signal into a plurality of modal functions, and solving the generalized fractal dimension of each modal component to perform feature extraction on the rolling bearing fault by constructing a generalized fractal dimension matrix.
S6: establishing a fine sketch of the rolling bearing fault using the signal state of health feature, the spectral feature, the entropy feature, and the multi-fractal dimension feature;
s7: and determining the occurrence position of the rolling bearing fault by using the fine image of the rolling bearing fault.
According to the rolling bearing fault diagnosis method based on the signal multi-dimensional fine image, the fine image of the rolling bearing fault is respectively subjected to feature extraction through four different aspects, such as: dimensionless feature value calculation, spectrum feature, entropy feature, multi-fractal dimension and the like. Although the signal can visually and intuitively show the health condition of the signal through the peak factor, the pulse factor, the margin factor and the kurtosis factor in the time domain, the situation that the internal structure of the signal cannot be obviously disclosed exists, and the spectrogram of the signal in the frequency domain effectively solves the defect that the internal structure of the signal is intuitively shown through envelope spectrum analysis. Meanwhile, in the frequency domain analysis, various different methods are adopted to further analyze and extract high and low rotating speeds, early faults and the like, so that fault characteristics under different conditions can be extracted. And decomposing the rolling bearing fault signal by using EMD, then respectively calculating singular entropy and sample entropy of IMF, and fusing to realize complementation between entropy characteristics to obtain fault characteristics richer than a certain entropy. Meanwhile, as the EMD entropy characteristics are overlapped sometimes, the KPCA characteristic extraction method is adopted to perform dimension reduction fusion on the EMD entropy characteristics so as to well separate the fault characteristics, improve the discrimination and the clustering performance and further better show the fault characteristics; meanwhile, the entropy feature extraction is carried out by using the fine composite multi-scale entropy, so that the problem that the undefined entropy is caused by too short sampling time sequence is solved, and the extraction of the fault feature of the rolling bearing is influenced. The rolling bearing fault signals are respectively subjected to corresponding feature extraction by using local feature scale decomposition and morphological fractal dimension as well as variational modal decomposition and generalized fractal dimension, and then the rolling bearing fault features extracted by the local feature scale decomposition and the morphological fractal dimension are combined to form a multi-fractal dimension feature, so that the fault features of the rolling bearing are more comprehensively shown.
While the present invention has been described in detail and with reference to the embodiments thereof as illustrated in the accompanying drawings, it will be apparent to one skilled in the art that various changes and modifications can be made therein. Therefore, certain details of the embodiments are not to be interpreted as limiting, and the scope of the invention is to be determined by the appended claims.
Claims (6)
1. A rolling bearing fault diagnosis method based on signal multi-dimensional fine image comprises the following steps:
s1: denoising the collected fault signal of a rolling bearing by using lifting wavelets;
s2: carrying out feature extraction in a time domain on the denoised fault signal to obtain signal health state features;
s3: carrying out feature extraction on the denoised fault signal to obtain a spectrum feature;
s4: carrying out feature extraction on the denoised fault signal to obtain entropy features;
s5: carrying out feature extraction on the denoised fault signal to obtain a multi-fractal dimension feature;
s6: establishing a fine sketch of the rolling bearing fault using the signal state of health feature, the spectral feature, the entropy feature, and the multi-fractal dimension feature;
s7: and determining the occurrence position of the rolling bearing fault by using the fine image of the rolling bearing fault.
2. The method of claim 1, wherein the signal state-of-health features comprise dimensionless features comprising a peak factor, a pulse factor, a margin factor, and a kurtosis factor.
3. The rolling bearing fault diagnosis method based on the signal multi-dimensional fine image according to claim 2, wherein the spectral features comprise fault features of a low-speed rolling bearing and early fault features of a rolling bearing; the S3 further includes the steps of:
s31: adopting a stress wave method of continuous wavelet analysis, establishing a mechanical model of the rolling bearing by using a finite element numerical analysis method, and extracting fault characteristics of the low-speed rolling bearing by extracting signal fault characteristic frequency from a reconstructed waveform after multi-scale decomposition and reconstruction processing are carried out on a stress wave signal;
s32: and performing feature extraction on the denoised fault signal of the rolling bearing by adopting multipoint optimal minimum entropy deconvolution correction and a square envelope spectrum, and extracting early fault features of the rolling bearing.
4. The rolling bearing fault diagnosis method based on the signal multi-dimensional fine image as claimed in claim 2, wherein the entropy features comprise EMD entropy features and fine composite multi-scale entropy features, and the EMD entropy features comprise EMD singular entropy and EMD sample entropy;
the step of S4 further includes the steps of:
s41: decomposing the fault signal after the rolling bearing is denoised by using an EMD method;
s42: respectively calculating the EMD singular entropy of the IMF and the EMD sample entropy and fusing to obtain the EMD entropy characteristics;
s43: and extracting the fine composite multi-scale entropy characteristics.
5. The rolling bearing fault diagnosis method based on the signal multi-dimensional fine image as claimed in claim 4, wherein the step of S42 is followed by a step of performing dimension reduction fusion on the EMD entropy features by adopting a KPCA feature extraction method.
6. The method for diagnosing the fault of the rolling bearing based on the signal multi-dimensional fine image as claimed in claim 2, wherein the multi-fractal dimension characteristics comprise a first fault characteristic and a second fault characteristic; the step of S5 further includes the steps of:
s51: performing feature extraction on the denoised fault signal of the rolling bearing by adopting local feature scale decomposition and morphological fractal dimension to obtain a first fault feature;
s52: performing feature extraction on the denoised fault signal of the rolling bearing by adopting variational modal decomposition and generalized fractal dimension to obtain a second fault feature;
s53: combining the first fault signature and the second fault signature to form the multi-fractal dimension signature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110178425.1A CN112985809A (en) | 2021-02-09 | 2021-02-09 | Rolling bearing fault diagnosis method based on signal multi-dimensional fine image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110178425.1A CN112985809A (en) | 2021-02-09 | 2021-02-09 | Rolling bearing fault diagnosis method based on signal multi-dimensional fine image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112985809A true CN112985809A (en) | 2021-06-18 |
Family
ID=76392803
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110178425.1A Pending CN112985809A (en) | 2021-02-09 | 2021-02-09 | Rolling bearing fault diagnosis method based on signal multi-dimensional fine image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112985809A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114323649A (en) * | 2021-12-31 | 2022-04-12 | 福州大学 | Slewing bearing fault diagnosis method based on CEEMDAN and PSO-MOMEDA |
| CN114994517A (en) * | 2022-07-04 | 2022-09-02 | 哈尔滨理工大学 | Soft fault diagnosis method for analog circuit |
| CN116358871A (en) * | 2023-03-29 | 2023-06-30 | 哈尔滨理工大学 | Rolling bearing weak signal composite fault diagnosis method based on graph rolling network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103439110A (en) * | 2013-07-31 | 2013-12-11 | 哈尔滨工程大学 | Early-stage weak fault diagnosis method of rolling bearing |
| CN104655423A (en) * | 2013-11-19 | 2015-05-27 | 北京交通大学 | Rolling bearing fault diagnosis method based on time-frequency domain multidimensional vibration feature fusion |
| CN105910823A (en) * | 2016-06-21 | 2016-08-31 | 上海电机学院 | Rolling bearing fault diagnosis method |
| CN108303255A (en) * | 2018-01-09 | 2018-07-20 | 内蒙古科技大学 | Low-speed heave-load device Fault Diagnosis of Roller Bearings, equipment and medium |
| CN110674892A (en) * | 2019-10-24 | 2020-01-10 | 北京航空航天大学 | Fault feature screening method based on weighted multi-feature fusion and SVM classification |
-
2021
- 2021-02-09 CN CN202110178425.1A patent/CN112985809A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103439110A (en) * | 2013-07-31 | 2013-12-11 | 哈尔滨工程大学 | Early-stage weak fault diagnosis method of rolling bearing |
| CN104655423A (en) * | 2013-11-19 | 2015-05-27 | 北京交通大学 | Rolling bearing fault diagnosis method based on time-frequency domain multidimensional vibration feature fusion |
| CN105910823A (en) * | 2016-06-21 | 2016-08-31 | 上海电机学院 | Rolling bearing fault diagnosis method |
| CN108303255A (en) * | 2018-01-09 | 2018-07-20 | 内蒙古科技大学 | Low-speed heave-load device Fault Diagnosis of Roller Bearings, equipment and medium |
| CN110674892A (en) * | 2019-10-24 | 2020-01-10 | 北京航空航天大学 | Fault feature screening method based on weighted multi-feature fusion and SVM classification |
Non-Patent Citations (7)
| Title |
|---|
| 冷军发等: "最小熵解卷积在滚动轴承早期故障诊断中的应用", 《机械传动》 * |
| 夏均忠等: "《基于改进信息图与MOMEDA的滚动轴承故障特征提取》", 《振动与冲击》 * |
| 孟宗等: "基于局部特征尺度分解和形态学分形维数的滚动轴承故障诊断方法", 《计量学报》 * |
| 应雨龙等: "基于多特征提取的滚动轴承故障诊断方法", 《上海电力学院学报》 * |
| 张淑清等: "基于VMD及广义分形维数矩阵的滚动轴承故障诊断", 《计量学报》 * |
| 王楠等: "基于应力波与小波分析的低速滚动轴承故障诊断研究", 《振动工程学报》 * |
| 许鹭等: "基于EMD熵特征融合的中介轴承故障特征提取方法", 《沈阳航空航天大学学报》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114323649A (en) * | 2021-12-31 | 2022-04-12 | 福州大学 | Slewing bearing fault diagnosis method based on CEEMDAN and PSO-MOMEDA |
| CN114994517A (en) * | 2022-07-04 | 2022-09-02 | 哈尔滨理工大学 | Soft fault diagnosis method for analog circuit |
| CN116358871A (en) * | 2023-03-29 | 2023-06-30 | 哈尔滨理工大学 | Rolling bearing weak signal composite fault diagnosis method based on graph rolling network |
| CN116358871B (en) * | 2023-03-29 | 2024-01-23 | 哈尔滨理工大学 | Rolling bearing weak signal composite fault diagnosis method based on graph rolling network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112985809A (en) | Rolling bearing fault diagnosis method based on signal multi-dimensional fine image | |
| Hamadache et al. | Principal component analysis based signal-to-noise ratio improvement for inchoate faulty signals: Application to ball bearing fault detection | |
| CN110595780B (en) | Bearing fault identification method based on vibration gray level image and convolution neural network | |
| CN109932179B (en) | Rolling bearing fault detection method based on DS self-adaptive spectrum reconstruction | |
| CN105716857A (en) | Planetary gearbox health state assessment method | |
| CN111238814A (en) | Rolling bearing fault diagnosis method based on short-time Hilbert transform | |
| CN110046476B (en) | Ternary binary fractal wavelet sparse diagnosis method for rolling bearing faults | |
| CN110717472B (en) | Fault diagnosis method and system based on improved wavelet threshold denoising | |
| CN112945546B (en) | Precise diagnosis method for complex faults of gearbox | |
| CN106771905B (en) | A kind of DISCHARGE PULSES EXTRACTION method suitable for high-frequency current Partial Discharge Detection | |
| CN114492538B (en) | Urban medium-voltage distribution cable partial discharge signal denoising method | |
| CN114112400A (en) | Mechanical bearing fault diagnosis method based on multi-angle information fusion | |
| CN111896260B (en) | NGAs synchronous optimization wavelet filter and MCKD bearing fault diagnosis method | |
| CN113325277A (en) | Partial discharge processing method | |
| CN110940522A (en) | Bearing fault periodic pulse sparse separation and diagnosis method under strong background noise | |
| CN104215456A (en) | Plane clustering and frequency-domain compressed sensing reconstruction based mechanical fault diagnosis method | |
| Xu et al. | Application of fast singular spectrum decomposition method based on order statistic filter in rolling bearing fault diagnosis | |
| CN110987433B (en) | Bearing fault early warning method based on high-frequency signal characteristic amplitude | |
| CN109724693B (en) | Fusion spectrum denoising method based on stationary wavelet | |
| Zhang et al. | Research on the fault diagnosis method for rolling bearings based on improved VMD and automatic IMF acquisition | |
| CN114486263A (en) | Noise reduction and demodulation method for vibration signal of rolling bearing of rotary machine | |
| Liu et al. | Maximum correntropy criterion-based blind deconvolution and its application for bearing fault detection | |
| CN113639985B (en) | Mechanical fault diagnosis and state monitoring method based on optimized fault characteristic frequency spectrum | |
| CN116361723A (en) | Bearing fault diagnosis and classification method based on multi-scale characteristics and attention | |
| CN116361733A (en) | Fault diagnosis method, device, system and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210618 |
|
| RJ01 | Rejection of invention patent application after publication |