CN113670616A - Bearing performance degradation state detection method and system - Google Patents
Bearing performance degradation state detection method and system Download PDFInfo
- Publication number
- CN113670616A CN113670616A CN202111034048.0A CN202111034048A CN113670616A CN 113670616 A CN113670616 A CN 113670616A CN 202111034048 A CN202111034048 A CN 202111034048A CN 113670616 A CN113670616 A CN 113670616A
- Authority
- CN
- China
- Prior art keywords
- bearing
- performance degradation
- index
- characteristic
- value
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Acoustics & Sound (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a method and a system for detecting the performance degradation state of a bearing, which comprises the following steps: s1, collecting vibration signals in the service process of the whole service life of the bearing; s2, constructing a high-dimensional degradation trend feature set, and performing smoothing treatment by using an exponential weighted moving average; s3, designing a characteristic sensitivity evaluation criterion, and screening out a characteristic sensitivity characteristic set of the performance degradation state of the bearing; and S4, fusing the sensitive feature set by using a uniform manifold approximation algorithm, and further smoothing the fusion index by using an exponential weighted moving average to form a bearing performance degradation state curve. The invention can remove noise in the characterization index and slow down the fluctuation in the degradation process of the bearing performance; the characterization index screening criterion is integrated with monotonicity and relevance in the process of bearing performance degradation, and effective characterization indexes can be selected more reasonably; the selected effective indexes are fused by using a consistent manifold approximation algorithm, the global structure and the local structure of the data can be considered, and the defects of the traditional data fusion method are overcome.
Description
Technical Field
The invention relates to the technical field of mechanical equipment health monitoring, in particular to a method and a system for detecting a performance degradation state of a bearing.
Background
Due to the development of sensors and computer technology, a great deal of condition monitoring data has been accumulated in industrial production. The data-driven method uses the state monitoring data to depict the degradation state of the bearing, rather than establishing a specific model which is not easy to obtain, and is widely used for bearing life prediction. In general, data-driven based bearing life prediction includes three steps: data acquisition, health index construction and residual life prediction. The health index is used for evaluating the degradation state of the service bearing by extracting features from the collected vibration data so as to quantify the historical degradation process of the service bearing. Therefore, the quality of the constructed health indicators directly affects the effectiveness of the data-driven prediction method. Therefore, it is very important to construct a characterization index capable of effectively describing the performance degradation state of the bearing.
At present, a single characterization index is used for state depiction, and if the single root mean square or wavelet information entropy is used as a health index for predicting the residual service life of the bearing. However, the characterization index is directly extracted from the original bearing vibration signal, and the disturbance of noise and other interference factors inevitably affects the quality of the existing characterization index, which is not beneficial to accurately depicting the degradation state of the bearing. Meanwhile, the single feature often reflects only the feature information of the part of the study object. Improving the performance of a single characterization index through data fusion is an effective scheme. However, how to obtain effective fusion feature information is the key of the feature fusion technology. The traditional health index construction method based on data fusion mainly comprises two steps: the first step is to map the vibration signal using a series of mathematical transformations to generate high dimensional features; and the second step is that the dimension of the high-dimensional feature is reduced through a dimension reduction method, so that sensitive low-dimensional information hidden in the high-dimensional feature is found. However, the conventional data fusion method cannot give consideration to the global structure and the local structure of the degradation state of the bearing, cannot comprehensively describe the degradation state of the bearing, and brings certain complexity to the subsequent bearing life prediction work. In general, the conventional method has the following three disadvantages: (1) the vibration signal of the bearing contains a large amount of noise and random fluctuation, and the harmful information can influence the trend of the index curve of the bearing and is not beneficial to describing the degradation state of the bearing. (2) Part of characteristics are not sensitive to the degradation degree of the bearing, and if the insensitive characteristics are directly fused, the degradation performance curve of the bearing is influenced, so that the insensitive characteristics need to be eliminated by adopting a reasonable scheme. (3) The traditional fusion dimension reduction method cannot give consideration to the global structure and the local structure of the bearing degradation state data.
Disclosure of Invention
The invention aims to provide a bearing performance degradation state detection method which can comprehensively detect the degradation state of a bearing and has high accuracy.
In order to solve the above problems, the present invention provides a bearing performance degradation state detection method, which includes the steps of:
s1, collecting vibration signals in the service process of the whole service life of the bearing;
s2, constructing a high-dimensional degradation trend feature set, and performing smoothing treatment by using an exponential weighted moving average;
s3, designing a characteristic sensitivity evaluation criterion, and screening out a characteristic sensitivity characteristic set of the performance degradation state of the bearing;
and S4, fusing the sensitive feature set by using a uniform manifold approximation algorithm, and further smoothing the fusion index by using an exponential weighted moving average to form a bearing performance degradation state curve.
As a further improvement of the invention, the high-dimensional degradation tendency feature set comprises statistical features in a time domain and statistical features in a frequency domain.
As a further improvement of the present invention, the statistical characteristics in the time domain include: mean, variance, standard deviation, square mean, root mean, absolute mean, root mean square, kurtosis, skewness, peak, kurtosis, entropy, skewness factor, kurtosis factor, waviness factor, impulse factor, and space factor in the time domain.
As a further improvement of the present invention, the statistical characteristics in the frequency domain include: the frequency mean value, the frequency center value, the frequency root mean square, the envelope spectrum frequency mean value, the envelope spectrum frequency center value and the envelope spectrum frequency root mean square in the frequency domain.
As a further improvement of the present invention, the calculation formula of the exponentially weighted moving average is as follows:
wherein x istFor the current observed value at the time t, xt' represents an estimated value thereof, i.e. a modified time series value at the time t, and α represents a smoothing parameter between 0 and 1.
As a further improvement of the invention, the value of alpha is 0.1.
As a further improvement of the present invention, the criterion CM for evaluating the characteristic sensitivity of the design is as follows:
wherein, Corr represents the linear correlation degree between the characteristic index and the sampling time t, and the calculation formula of Corr is as follows:
wherein K represents the time sequence length of the characterization index, HI (t)k) And T (T)k) Respectively representing the token index and a time vector from 1 to K,
and
are HI (t) respectivelyk) And T (T)k) The mean value of (a);
mon represents the monotonicity of the curve, the monotonicity of the characteristic index curve is evaluated by the positive and negative number of the difference value of two adjacent characteristic index values, if the total number of positive values is larger than the total number of negative values, the monotonicity is shown to rise, and vice versa; when the Mon value is close to 0, the monotonicity of the characterization index curve is poor, and the closer the Mon value is to 1, the better the monotonicity of the characterization index curve is; the calculation formula for Mon is as follows:
dHI (t) among themk) Represented by two adjacent HIs (t)k) No. of (. cndot.) represents the number of (. cndot.) s.
As a further improvement of the method, indexes describing the performance degradation state of the bearing are screened out by setting a threshold value, and the CM threshold value is between 0.45 and 0.5.
As a further improvement of the present invention, step S4 includes:
s41, searching n nearest neighbors of the sensitive feature set of each moment point, generating a normalized distance on a manifold, converting a limited measurement space into a pure set, and constructing a local fuzzy pure set of state points at all moments through iteration;
s42, forming a global fuzzy topological representation by utilizing a union set of local fuzzy pure sets, and performing spectrum embedding on a symmetric normalized Laplacian by using a standard spectrum method;
s43, minimizing cross entropy among topological representations by using a random gradient descent method to obtain optimized low-dimensional embedding;
and S44, outputting the optimized low-dimensional embedding as a fusion index, and further smoothing the fusion index by utilizing an exponential weighted moving average to form a bearing performance degradation state curve.
The invention also provides a bearing performance degradation state detection system, which comprises:
the signal acquisition module is used for acquiring vibration signals in the service process of the whole service life of the bearing;
the characteristic set construction module is used for constructing a high-dimensional degradation trend characteristic set;
the first characteristic fusion module is used for carrying out characteristic fusion and smoothing by using exponential weighted moving average;
the sensitive feature set screening module is used for designing a feature sensitivity evaluation criterion and screening out a sensitive feature set of the performance degradation state of the bearing;
the sensitive feature set fusion module is used for fusing the sensitive feature set by utilizing a uniform manifold approximation algorithm;
and the second characteristic fusion module is used for further smoothing the fusion indexes by using the exponential weighted moving average to form a bearing performance degradation state curve.
The invention has the beneficial effects that:
the bearing performance degradation state detection method and the system index weighted moving average algorithm can remove noise in the characterization index and slow down fluctuation in the bearing performance degradation process; the designed characterization index screening criterion is integrated with monotonicity and relevance in the process of bearing performance degradation, and effective characterization indexes can be selected more reasonably; the selected effective indexes are fused by using a consistent manifold approximation algorithm, the global structure and the local structure of the data can be considered, so that the defects of the traditional data fusion method are overcome, and the detection accuracy is effectively improved.
Meanwhile, the richness of the source of the characterization indexes, the reasonability of the evaluation criterion of the selection of the characterization indexes and the advancement of the fusion algorithm are fused to comprehensively ensure that the constructed characterization indexes have high-quality characteristics and overcome the limitations of single property indexes and traditional fusion indexes.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood, the present invention may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present invention more clearly understood, the following preferred embodiments are described in detail with reference to the accompanying drawings.
Drawings
Fig. 1 is a flowchart of a bearing performance degradation state detection method in a preferred embodiment of the present invention.
Detailed Description
The present invention is further described below in conjunction with the following figures and specific examples so that those skilled in the art may better understand the present invention and practice it, but the examples are not intended to limit the present invention.
As shown in fig. 1, the method for detecting the performance degradation state of the bearing in the preferred embodiment of the present invention includes the following steps:
s1, collecting vibration signals in the service process of the whole service life of the bearing;
s2, constructing a high-dimensional degradation trend feature set, and performing smoothing treatment by using an exponential weighted moving average;
s3, designing a characteristic sensitivity evaluation criterion, and screening out a characteristic sensitivity characteristic set of the performance degradation state of the bearing;
and S4, fusing the sensitive feature set by using a uniform manifold approximation algorithm, and further smoothing the fusion index by using an exponential weighted moving average to form a bearing performance degradation state curve.
Wherein the high-dimensional degradation tendency feature set comprises statistical features in a time domain and statistical features in a frequency domain.
Specifically, the statistical features in the time domain include: mean, variance, standard deviation, square mean, root mean, absolute mean, root mean square, kurtosis, skewness, peak, kurtosis, entropy, skewness factor, kurtosis factor, waviness factor, impulse factor, and space factor in the time domain. The statistical features in the frequency domain include: the frequency mean value, the frequency center value, the frequency root mean square, the envelope spectrum frequency mean value, the envelope spectrum frequency center value and the envelope spectrum frequency root mean square in the frequency domain.
The calculation formula of the exponentially weighted moving average in steps S2 and S4 is as follows:
wherein the content of the first and second substances,xtis the current observed value at time t, x'tRepresenting its estimated value, i.e. the modified time series value at time t, alpha represents a smoothing parameter between 0 and 1. Preferably, α is 0.1.
In some embodiments, the design's feature sensitivity evaluation criterion CM is as follows:
where Corr represents the degree of linear correlation, i.e. the trend, between the characteristic index and the sampling time t. The ideal health index value curve should also gradually increase or decrease with time, showing a better trend. The closer the absolute value of Corr is to 1, the stronger the linear correlation with the sampling time, the stronger the trend, and vice versa. The calculation of Corr is as follows:
wherein K represents the time sequence length of the characterization index, HI (t)k) And T (T)k) Respectively representing the token index and a time vector from 1 to K,
and
are HI (t) respectivelyk) And T (T)k) The mean value of (a);
mon represents the monotonicity of the curve, the monotonicity of the characteristic index curve is evaluated by the positive and negative number of the difference value of two adjacent characteristic index values, if the total number of positive values is larger than the total number of negative values, the monotonicity is shown to rise, and vice versa; when the Mon value is close to 0, the monotonicity of the characterization index curve is poor, and the closer the Mon value is to 1, the better the monotonicity of the characterization index curve is; the calculation formula for Mon is as follows:
dHI (t) among themk) Represented by two adjacent HIs (t)k) No. of (. cndot.) represents the number of (. cndot.) s.
When the CM is used for screening the sensitive characteristic indexes, the higher the value of the characteristic sensitivity evaluation criterion CM is, the condition characteristic can better represent the performance degradation condition of the bearing. Therefore, indexes which can describe the performance degradation state of the bearing are screened out by setting a threshold value, and the recommended CM threshold value is 0.45-0.5.
Specifically, step S4 includes the following steps:
s41, searching n nearest neighbors of the sensitive feature set of each moment point, generating a normalized distance on a manifold, converting a limited measurement space into a pure set, and constructing a local fuzzy pure set of state points at all moments through iteration;
s42, forming a global fuzzy topological representation by utilizing a union set of local fuzzy pure sets, and performing spectrum embedding on a symmetric normalized Laplacian by using a standard spectrum method;
s43, minimizing cross entropy among topological representations by using a random gradient descent method to obtain optimized low-dimensional embedding;
and S44, outputting the optimized low-dimensional embedding as a fusion index, and further smoothing the fusion index by utilizing an exponential weighted moving average to form a bearing performance degradation state curve.
The preferred embodiment of the invention also discloses a bearing performance degradation state detection system, which comprises the following modules:
the signal acquisition module is used for acquiring vibration signals in the service process of the whole service life of the bearing;
the characteristic set construction module is used for constructing a high-dimensional degradation trend characteristic set;
the first characteristic fusion module is used for carrying out characteristic fusion and smoothing by using exponential weighted moving average;
the sensitive feature set screening module is used for designing a feature sensitivity evaluation criterion and screening out a sensitive feature set of the performance degradation state of the bearing;
the sensitive feature set fusion module is used for fusing the sensitive feature set by utilizing a uniform manifold approximation algorithm;
and the second characteristic fusion module is used for further smoothing the fusion indexes by using the exponential weighted moving average to form a bearing performance degradation state curve.
The method involved in the system for detecting the performance degradation state of the bearing in this embodiment is the same as that in the above embodiment, and is not described herein again.
The bearing performance degradation state detection method and the system index weighted moving average algorithm can remove noise in the characterization index and slow down fluctuation in the bearing performance degradation process; the designed characterization index screening criterion is integrated with monotonicity and relevance in the process of bearing performance degradation, and effective characterization indexes can be selected more reasonably; the selected effective indexes are fused by using a consistent manifold approximation algorithm, and the global structure and the local structure of the data can be considered so as to make up for the defects of the traditional data fusion method.
Meanwhile, the richness of the source of the characterization indexes, the reasonability of the evaluation criterion of the selection of the characterization indexes and the advancement of the fusion algorithm are fused to comprehensively ensure that the constructed characterization indexes have high-quality characteristics and overcome the limitations of single property indexes and traditional fusion indexes.
The above embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (10)
1. A bearing performance degradation state detection method is characterized by comprising the following steps:
s1, collecting vibration signals in the service process of the whole service life of the bearing;
s2, constructing a high-dimensional degradation trend feature set, and performing smoothing treatment by using an exponential weighted moving average;
s3, designing a characteristic sensitivity evaluation criterion, and screening out a characteristic sensitivity characteristic set of the performance degradation state of the bearing;
and S4, fusing the sensitive feature set by using a uniform manifold approximation algorithm, and further smoothing the fusion index by using an exponential weighted moving average to form a bearing performance degradation state curve.
2. The method of claim 1, wherein the high-dimensional degradation tendency feature set comprises statistical features in a time domain and statistical features in a frequency domain.
3. The method of detecting a state of performance degradation of a bearing of claim 2, wherein the statistical features in the time domain comprise: mean, variance, standard deviation, square mean, root mean, absolute mean, root mean square, kurtosis, skewness, peak, kurtosis, entropy, skewness factor, kurtosis factor, waviness factor, impulse factor, and space factor in the time domain.
4. The method of detecting a state of bearing performance degradation according to claim 2, wherein the statistical features in the frequency domain include: the frequency mean value, the frequency center value, the frequency root mean square, the envelope spectrum frequency mean value, the envelope spectrum frequency center value and the envelope spectrum frequency root mean square in the frequency domain.
5. The method for detecting a degraded state of a bearing according to claim 1, wherein the calculation formula of the exponentially weighted moving average is as follows:
wherein x istIs the current observed value at time t, x'tRepresenting its estimated value, i.e. the modified time series value at time t, alpha represents a smoothing parameter between 0 and 1.
6. The method for detecting a performance degradation state of a bearing of claim 5, wherein α is 0.1.
7. The method for detecting a degraded state of bearing performance according to claim 1, wherein the criterion CM for evaluating the characteristic sensitivity of the design is as follows:
wherein, Corr represents the linear correlation degree between the characteristic index and the sampling time t, and the calculation formula of Corr is as follows:
wherein K represents the time sequence length of the characterization index, HI (t)k) And T (T)k) Respectively representing the token index and a time vector from 1 to K,
and
are HI (t) respectivelyk) And T (T)k) The mean value of (a);
mon represents the monotonicity of the curve, the monotonicity of the characteristic index curve is evaluated by the positive and negative number of the difference value of two adjacent characteristic index values, if the total number of positive values is larger than the total number of negative values, the monotonicity is shown to rise, and vice versa; when the Mon value is close to 0, the monotonicity of the characterization index curve is poor, and the closer the Mon value is to 1, the better the monotonicity of the characterization index curve is; the calculation formula for Mon is as follows:
dHI (t) among themk) Represented by two adjacent HIs (t)k) No. of (. cndot.) represents the number of (. cndot.) s.
8. The method for detecting the performance degradation state of the bearing according to claim 7, wherein the index describing the performance degradation state of the bearing is screened out by setting a threshold value, and the CM threshold value is between 0.45 and 0.5.
9. The method for detecting a degraded state of bearing performance as claimed in claim 1, wherein the step S4 includes:
s41, searching n nearest neighbors of the sensitive feature set of each moment point, generating a normalized distance on a manifold, converting a limited measurement space into a pure set, and constructing a local fuzzy pure set of state points at all moments through iteration;
s42, forming a global fuzzy topological representation by utilizing a union set of local fuzzy pure sets, and performing spectrum embedding on a symmetric normalized Laplacian by using a standard spectrum method;
s43, minimizing cross entropy among topological representations by using a random gradient descent method to obtain optimized low-dimensional embedding;
and S44, outputting the optimized low-dimensional embedding as a fusion index, and further smoothing the fusion index by utilizing an exponential weighted moving average to form a bearing performance degradation state curve.
10. A bearing performance degradation state detection system, comprising:
the signal acquisition module is used for acquiring vibration signals in the service process of the whole service life of the bearing;
the characteristic set construction module is used for constructing a high-dimensional degradation trend characteristic set;
the first characteristic fusion module is used for carrying out characteristic fusion and smoothing by using exponential weighted moving average;
the sensitive feature set screening module is used for designing a feature sensitivity evaluation criterion and screening out a sensitive feature set of the performance degradation state of the bearing;
the sensitive feature set fusion module is used for fusing the sensitive feature set by utilizing a uniform manifold approximation algorithm;
and the second characteristic fusion module is used for further smoothing the fusion indexes by using the exponential weighted moving average to form a bearing performance degradation state curve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111034048.0A CN113670616B (en) | 2021-09-03 | 2021-09-03 | Bearing performance degradation state detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111034048.0A CN113670616B (en) | 2021-09-03 | 2021-09-03 | Bearing performance degradation state detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113670616A true CN113670616A (en) | 2021-11-19 |
| CN113670616B CN113670616B (en) | 2022-12-06 |
Family
ID=78548439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111034048.0A Active CN113670616B (en) | 2021-09-03 | 2021-09-03 | Bearing performance degradation state detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113670616B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114647909A (en) * | 2022-04-02 | 2022-06-21 | 江苏科技大学 | Method for determining rolling bearing degradation point based on maximum value of spectral kurtosis characteristic |
| CN114782453A (en) * | 2022-06-23 | 2022-07-22 | 张家港Aaa精密制造股份有限公司 | Bearing quality detection method and system based on intelligent manufacturing |
| CN115310490A (en) * | 2022-08-17 | 2022-11-08 | 中国核动力研究设计院 | Rotating equipment fault analysis method based on multi-domain feature and sensitive feature selection |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103954450A (en) * | 2014-05-19 | 2014-07-30 | 重庆交通大学 | Bearing life degradation performance evaluation index construction method based on main component analysis |
| CN107727395A (en) * | 2017-07-21 | 2018-02-23 | 中国矿业大学 | A kind of Method for Bearing Fault Diagnosis assessed based on full variation and uncompensation distance |
| CN110057584A (en) * | 2019-04-01 | 2019-07-26 | 西安交通大学 | A kind of locomotive traction motor bearing degradation monitoring method |
| CN111680661A (en) * | 2020-06-19 | 2020-09-18 | 哈尔滨工业大学 | Mechanical rotating part performance degradation tracking method based on multi-feature fusion |
| CN112597607A (en) * | 2020-12-21 | 2021-04-02 | 北京华能新锐控制技术有限公司 | Predictive maintenance method and system for high-speed bearing of wind driven generator |
-
2021
- 2021-09-03 CN CN202111034048.0A patent/CN113670616B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103954450A (en) * | 2014-05-19 | 2014-07-30 | 重庆交通大学 | Bearing life degradation performance evaluation index construction method based on main component analysis |
| CN107727395A (en) * | 2017-07-21 | 2018-02-23 | 中国矿业大学 | A kind of Method for Bearing Fault Diagnosis assessed based on full variation and uncompensation distance |
| CN110057584A (en) * | 2019-04-01 | 2019-07-26 | 西安交通大学 | A kind of locomotive traction motor bearing degradation monitoring method |
| CN111680661A (en) * | 2020-06-19 | 2020-09-18 | 哈尔滨工业大学 | Mechanical rotating part performance degradation tracking method based on multi-feature fusion |
| CN112597607A (en) * | 2020-12-21 | 2021-04-02 | 北京华能新锐控制技术有限公司 | Predictive maintenance method and system for high-speed bearing of wind driven generator |
Non-Patent Citations (1)
| Title |
|---|
| 王奉涛等: "流形模糊C均值方法及其在滚动轴承性能退化评估中的应用", 《机械工程学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114647909A (en) * | 2022-04-02 | 2022-06-21 | 江苏科技大学 | Method for determining rolling bearing degradation point based on maximum value of spectral kurtosis characteristic |
| CN114647909B (en) * | 2022-04-02 | 2023-04-21 | 江苏科技大学 | Method for determining degradation point of rolling bearing based on spectral kurtosis characteristic maximum value |
| CN114782453A (en) * | 2022-06-23 | 2022-07-22 | 张家港Aaa精密制造股份有限公司 | Bearing quality detection method and system based on intelligent manufacturing |
| CN115310490A (en) * | 2022-08-17 | 2022-11-08 | 中国核动力研究设计院 | Rotating equipment fault analysis method based on multi-domain feature and sensitive feature selection |
| CN115310490B (en) * | 2022-08-17 | 2024-03-29 | 中国核动力研究设计院 | Rotary equipment fault analysis method based on multi-domain feature and sensitive feature selection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113670616B (en) | 2022-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113670616B (en) | Bearing performance degradation state detection method and system | |
| Rajabi et al. | A comparative study of clustering techniques for electrical load pattern segmentation | |
| Wang et al. | A novel weighted sparse representation classification strategy based on dictionary learning for rotating machinery | |
| Yiakopoulos et al. | Rolling element bearing fault detection in industrial environments based on a K-means clustering approach | |
| Zhang et al. | An adaptive outlier detection and processing approach towards time series sensor data | |
| CN112036042B (en) | Power equipment abnormality detection method and system based on variational modal decomposition | |
| CN110705722A (en) | Diagnostic model for industrial equipment fault diagnosis and construction method and application thereof | |
| CN111881594B (en) | Non-stationary signal state monitoring method and system for nuclear power equipment | |
| Zhao et al. | A novel deep fuzzy clustering neural network model and its application in rolling bearing fault recognition | |
| CN116644284A (en) | Stratum classification characteristic factor determining method, system, electronic equipment and medium | |
| CN113670186A (en) | GNSS deformation monitoring denoising method combining variational modal decomposition and permutation entropy | |
| CN115165274A (en) | Self-adaptive intelligent monitoring device and method for vibration state of engineering mechanical equipment | |
| CN117131110A (en) | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis | |
| Meng et al. | A gear fault diagnosis method based on improved accommodative random weighting algorithm and BB-1D-TP | |
| CN117172601A (en) | Non-invasive load monitoring method based on residual total convolution neural network | |
| Wu et al. | Universal window size-dependent transition of correlations in complex systems | |
| CN115310499B (en) | Industrial equipment fault diagnosis system and method based on data fusion | |
| Shu et al. | A Comprehensive working condition identification scheme for rolling bearings based on modified CEEMDAN as well as modified hierarchical amplitude-aware permutation entropy | |
| CN114819260A (en) | Dynamic generation method of hydrologic time series prediction model | |
| Ancona-Navarrete et al. | Diagnostics for pairwise extremal dependence in spatial processes | |
| CN112069621B (en) | Method for predicting residual service life of rolling bearing based on linear reliability index | |
| Xiao et al. | Intelligent fault diagnosis of gear crack based on side frequency feature under different working conditions | |
| CN115249059A (en) | Model training and abnormal data analysis method and device and computer storage medium | |
| Zhang et al. | Fault pattern recognition of rolling bearing based on smoothness prior approach and dual-input depth spatial–temporal fusion | |
| CN117290742B (en) | Signal time sequence data fault diagnosis method and system based on dynamic clustering |
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 |