CN114813119A - Multi-source information fusion-based performance degradation evaluation method for miniature turbine bearing - Google Patents
Multi-source information fusion-based performance degradation evaluation method for miniature turbine bearing Download PDFInfo
- Publication number
- CN114813119A CN114813119A CN202210270292.5A CN202210270292A CN114813119A CN 114813119 A CN114813119 A CN 114813119A CN 202210270292 A CN202210270292 A CN 202210270292A CN 114813119 A CN114813119 A CN 114813119A
- Authority
- CN
- China
- Prior art keywords
- bearing
- factor
- performance degradation
- signal
- peak
- 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
- 238000006731 degradation reaction Methods 0.000 title claims abstract description 41
- 230000015556 catabolic process Effects 0.000 title claims abstract description 39
- 238000011156 evaluation Methods 0.000 title claims abstract description 14
- 230000004927 fusion Effects 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 39
- 230000001133 acceleration Effects 0.000 claims abstract description 28
- 230000008569 process Effects 0.000 claims abstract description 25
- 238000000513 principal component analysis Methods 0.000 claims abstract description 23
- 238000006073 displacement reaction Methods 0.000 claims abstract description 21
- 238000013210 evaluation model Methods 0.000 claims abstract description 10
- 239000013598 vector Substances 0.000 claims description 31
- 238000005096 rolling process Methods 0.000 claims description 14
- 230000004044 response Effects 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 3
- 238000012512 characterization method Methods 0.000 claims description 2
- 230000009467 reduction Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 abstract description 5
- 238000003745 diagnosis Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 238000005299 abrasion Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 241001391944 Commicarpus scandens Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001050 lubricating effect Effects 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000518 rheometry Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000002759 z-score normalization 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (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)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides a performance degradation evaluation method for a micro turbine bearing based on multi-source information fusion, and belongs to the technical field of fault diagnosis. According to the method, an initial characteristic set is established by extracting time domain and frequency domain characteristic values of an acceleration signal, a displacement signal and a temperature signal, after the initial characteristic values are normalized, principal characteristics in the bearing performance degradation process are obtained by using PCA (principal component analysis), and the principal characteristics are introduced into k-medoid calibration to establish a performance degradation evaluation model. The difference between the main characteristics and the normal center in the whole process of the bearing performance degradation is used as a degradation factor. The test result verifies the effectiveness of the model established by the invention. The state evaluation model established by the invention has good tendency and can effectively represent the whole process of the performance degradation of the bearing of the micro turbine through comparison with the time domain characteristic parameters and the degradation factors based on the Euclidean distance.
Description
Technical Field
The invention belongs to the technical field of fault diagnosis, and particularly relates to a method for evaluating performance degradation of a bearing of a micro turbine based on multi-source information fusion.
Background
Rolling bearings are key parts in rotating machinery, particularly for micro turbines represented by turbochargers, micro gas turbines and the like, the bearings are used as weak links in rotor systems of the micro turbines, are particularly affected by improper installation and the like, are easy to break down, shorten the service life of the bearings, affect the stable operation of the whole machine, and cause sudden shutdown of the whole machine in severe cases to affect the personal and property safety. Therefore, the method has the advantages that the state monitoring and the performance degradation evaluation are carried out in the service process of the bearing of the micro turbine, the fault is found in time, the maintenance is carried out according to the situation, the stable operation of the rotor system of the micro turbine is ensured, the sudden stop is avoided, the occurrence of major accidents is prevented, and the significance is great.
At present, the monitoring and evaluation of the bearing state at home and abroad mainly comprises the steps of processing vibration data in the whole life process of the bearing to obtain characteristic parameters of time domains such as root mean square, kurtosis, peak value and crest factor, or extracting the characteristic parameters of a vibration signal and constructing a proper and robust bearing performance degradation evaluation method by combining an intelligent evaluation model, and the method achieves certain effect. However, these indices are sometimes insufficient in sensitivity or continuity to be used alone. For example, kurtosis values, crest factors, and pulse factors are particularly effective for the initial stages, and these metrics will decrease to normal levels as defect size increases. In addition, the micro turbine bearing has a severe operating environment and serious noise interference, and the difficulty of evaluating the performance degradation of the bearing is increased.
In the running process of the rolling bearing, the service performance of the rolling bearing is influenced by factors in the aspects of friction, abrasion and lubrication mechanisms, fluid dynamics, lubricating medium rheology, material performance, contact mechanics and the like, and the performance degradation process of the rolling bearing is a multi-source information response process integrating the changes of factors such as vibration, temperature and the like due to the changes of plastic deformation, rolling contact abrasion and fatigue of the surface of a material. Therefore, the development of the bearing performance degradation evaluation based on the multi-source response fusion has potential possibility of improving the evaluation effect.
Disclosure of Invention
The invention provides a novel method for evaluating the performance degradation of a bearing based on multi-source information fusion aiming at the condition monitoring and the performance evaluation of a bearing of a miniature turbine. The method comprises the steps of establishing an initial characteristic set by extracting time domain and frequency domain characteristic values of acceleration signals, displacement signals and temperature signals, normalizing the initial characteristic values, utilizing PCA to reduce dimensions to obtain main characteristics in the process of bearing performance degradation, introducing the main characteristics into a k-center clustering algorithm, and establishing a performance degradation evaluation model. The difference between the main characteristics and the normal center in the whole process of the bearing performance degradation is used as a degradation factor. The test result verifies the effectiveness of the model established by the invention. The state evaluation model established by the invention has good tendency and can effectively represent the whole process of the performance degradation of the bearing of the micro turbine through comparison with the time domain characteristic parameters and the degradation factors based on the Euclidean distance.
The technical scheme of the invention is as follows:
a performance degradation evaluation method for a micro turbine bearing based on multi-source information fusion comprises the following steps:
step 1: and establishing a characteristic sample set based on the bearing seat acceleration signal, the rotating shaft displacement signal and the temperature signal on the characteristic fusion level.
Step 1.1: continuous sampling, collecting multi-source response signals including acceleration signal V of bearing during operation of bearing of microturbine b Rotation axis displacement signal V s And a bearing housing temperature signal T.
Step 1.2: and (3) respectively extracting the characteristic parameters of the multi-source response signals in the step 1.1, and constructing an initial characteristic sample set.
Initial set of feature samples W p*q The method comprises the time-frequency domain characteristic parameters of the acceleration signals, the time domain characteristic parameters of the displacement signals and the mean value of the temperature signals. The specific characteristic parameters are as follows: extracting bearing acceleration signal V b The time domain characteristic parameter of (2): peak-to-peak, mean, root-mean-square, variance, standard deviation, kurtosis, form factor, peak factor, pulse factor, and margin factor; extracting bearing acceleration signal V b Frequency domain characteristic parameters of (2): inner ring rotation frequency f r And frequency f of passing of the rolling body on the outer ring bo Passing frequency f of rolling element in inner ring bi And the revolution frequency f of the cage c Rolling element rotation frequency f b . Extracting a displacement signal V of a rotating shaft s Time domain characteristic parameter of (2): peak-to-peak, mean, root-mean-square, variance, standard deviation, kurtosis, form factor, peak factor, pulse factor, and margin factor. For the temperature signal T: and taking the average value of the temperatures of the three measuring points.
Step 1.3: and (3) normalizing the characteristic parameters in the step 1.2, so as to eliminate the difference between the characteristic parameters caused by different dimensions. The commonly used normalization methods include the maximum-minimum normalization and the z-score normalization, the maximum-minimum normalization method is adopted in the invention, and the corresponding formula is as follows:
in the formula, w k For the k-th feature vector,
is the corresponding normalized feature vector.
Step 1.4: and obtaining a characteristic vector representing the running state of the bearing based on the dimensionality reduction treatment of the PCA.
For normalized feature set
Introducing PCA (principal component analysis) to obtain a principal component PC (principal component analysis) of the feature set, namely the principal component with the highest variance, thereby constructing a feature vector f for representing the running state of the bearing PC And feature matrix F p*n 。
Firstly, the covariance of the normalized feature vector is calculated, and the specific calculation formula is as follows:
wherein S is k Is normalized k-th feature vector
Covariance of (2), m k Is the corresponding average vector and T represents the matrix transpose.
Then, S is obtained k The eigenvector corresponding to the largest eigenvalue is the first principal component, and so on for the remaining principal components.
Step 2: constructing a state evaluation model based on k-center clustering
Step 2.1: feature vector f of normal state and failure state PC Introducing a k-medoids clustering algorithm to obtain a clustering center C at a normal stage and a failure stage Nor And C Fai 。
Step 2.2: respectively utilizing squared Euclidean distance and membership function to calculate other state characteristic vector and C in bearing operation process Nor 、C Fai As a degradation factor DI characterizing the degradation of the bearing performance. The shorter the distance, the smaller the difference. Thus, a larger distance indicates a more severe degradation of the bearing performance.
Wherein, the expression for calculating DI by using squared Euclidean distance is as follows:
wherein h is less than n, h is the number of classifications, and n is the feature vector f PC The number of the cells;
is an arbitrary characteristic parameter; c. C i Is the cluster center.
The expression for DI is calculated using the membership functions as:
wherein r ═2, subscript D *A (xis xy or ty) represents the 2-norm of the calculation vector.
For a brief and concise characterization of the bearing operation process, DI is further transformed into a Confidence Value (CV) between 0 and 1, as shown in equation (6).
CV＝exp(-DI/c) (6)
Wherein c is a scale value. When the bearing fails, the CV value tends to 0.
The invention has the beneficial effects that: the invention provides a novel method for evaluating the performance degradation of a bearing based on multi-source information fusion. The method comprises the steps of establishing an initial characteristic set by extracting time domain and frequency domain characteristic values of acceleration signals, displacement signals and temperature signals, normalizing the initial characteristic values, utilizing PCA to reduce dimensions to obtain main characteristics in the process of bearing performance degradation, introducing the main characteristics into k-medoids clustering, and establishing a performance degradation evaluation model. The difference between the main characteristics and the normal center in the whole process of the bearing performance degradation is used as a degradation factor. The test result verifies the effectiveness of the model established by the invention. The state evaluation model established by the invention has good tendency and can effectively represent the whole process of the performance degradation of the bearing of the micro turbine through comparison with the time domain characteristic parameters and the degradation factors based on the Euclidean distance.
Drawings
FIG. 1 is a schematic view of a test stand for a bearing-rotor system of a micro-turbine and the location of the sensor mounting. The device comprises a sensor, a sensor and a controller, wherein a and b are eddy current sensors for measuring displacement signals, a is used for measuring horizontal displacement of a rotating shaft, and b is used for measuring vertical displacement of the rotating shaft; c. d is a piezoelectric acceleration sensor for measuring the acceleration signals of the tested bearing and the comparison bearing; e. f and g are k-type thermocouple sensors which are uniformly distributed along the circumferential direction of the bearing seat, and the e-type thermocouple and the d-type acceleration sensor form an angle of 15 degrees.
Fig. 2 is a flowchart of bearing performance degradation evaluation.
FIG. 3 is a time-frequency domain diagram of an acceleration signal. Wherein, (a) - (d) are time domain diagrams of four stages of normal, mild, severe and failure in the bearing operation process; (e) - (h) is a frequency domain plot of the normal, mild, severe and failure four stages of the bearing operation process.
Fig. 4 is a time-frequency domain diagram of a displacement signal. Wherein, (a) - (d) are time domain diagrams of four stages of normal, mild, severe and failure in the bearing operation process; (e) - (h) is a frequency domain plot of the normal, mild, severe and failure four stages of the bearing operation process.
FIG. 5 is a three-point temperature evolution curve of the bearing seat.
FIG. 6 is a time-domain characteristic parameter (peak-to-peak value, effective value and kurtosis value) evolution curve of the bearing acceleration signal.
FIG. 7 shows the k-medoids clustering results.
Fig. 8(a) and 8(b) are evolution curves of CVs values (for an acceleration signal, a displacement signal and a temperature signal) of the bearing whole life process obtained based on the euclidean distance squared and the membership function, respectively.
Fig. 9 is an evolution curve of CVs values (for acceleration signals) over the life of a bearing obtained based on membership functions.
Detailed Description
The following describes an embodiment of the present invention in further detail with reference to the accompanying drawings and technical solutions.
The method comprises the following specific steps:
step 1: and establishing a characteristic sample set based on the bearing seat acceleration signal, the rotating shaft displacement signal and the temperature signal on the characteristic fusion level.
Step 1.1: continuously sampling for 1818s to obtain multi-source response signals including acceleration signal V of bearing during operation of bearing of microturbine b Rotation axis displacement signal V s And a bearing housing temperature signal T.
FIG. 1 shows a test bed of a bearing-rotor system of a micro-turbine and the mounting locations of sensors to obtain multi-source response signals over the life of the bearing.
The distribution of the acceleration and rotating shaft displacement time-frequency domain graphs in four stages of normal, slight, severe and failure in the bearing operation process is shown in figures 4 and 5. FIG. 6 shows a temperature evolution curve of three measuring points of a bearing seat.
Step 1.2: and (3) respectively extracting the characteristic parameters of the multi-source response signals in the step 1.1, and constructing an initial characteristic sample set.
Initial set of feature samples W p*q The method comprises the time-frequency domain characteristic parameters of the acceleration signals, the time domain characteristic parameters of the displacement signals and the mean value of the temperature signals. The specific characteristic parameters are as follows: extracting bearing acceleration signal V b Time domain characteristic parameter of (2): peak-to-peak, mean, root-mean-square, variance, standard deviation, kurtosis, form factor, peak factor, pulse factor, and margin factor; extracting bearing acceleration signal V b Frequency domain characteristic parameters of (2): inner ring rotation frequency f r And frequency f of passing of the rolling body on the outer ring bo Passing frequency f of rolling element in inner ring bi The revolution frequency f of the cage c Rolling element rotation frequency f b . Extracting a displacement signal V of a rotating shaft s Time domain characteristic parameter of (2): peak-to-peak, mean, root-mean-square, variance, standard deviation, kurtosis, form factor, peak factor, pulse factor, and margin factor. For the temperature signal T: and taking the average value of the temperatures of the three measuring points.
FIG. 6 is a time-domain characteristic parameter (peak-to-peak value, effective value and kurtosis value) evolution curve of the bearing acceleration signal.
Step 1.3: and (3) normalizing the characteristic parameters in the step 1.2, so as to eliminate the difference between the characteristic parameters caused by different dimensions. The maximum and minimum normalization method is adopted, and the corresponding formula is as follows:
in the formula, w k For the k-th feature vector,
is the corresponding normalized feature vector.
Step 1.4: for normalized feature set
Introducing into PCA to obtain the compoundPrincipal component PC of the syndrome, i.e., the principal component with the highest variance, to construct a feature vector f characterizing the operating condition of the bearing PC And feature matrix F p*n 。
Firstly, the covariance of the normalized feature vector is calculated, and the specific calculation formula is as follows:
wherein S is k Is normalized k-th feature vector
Covariance of (2), m k Is the corresponding average vector and T represents the matrix transpose.
Then, S is obtained k The eigenvector corresponding to the largest eigenvalue is the first principal component, and so on for the remaining principal components.
As shown in fig. 2, the evaluation steps of the bearing performance degradation based on multi-source signal fusion are as follows:
step 2: constructing a state evaluation model based on k-center clustering
Step 2.1: the k-medoids clustering model is trained by using the characteristic vectors of the normal state (190 characteristic vectors) and the failure state (190 characteristic vectors) in the bearing life process, and after the training is finished, the clustering centers of the normal state and the failure state can be obtained, and the specific result is shown in fig. 7.
Step 2.2: the difference between the main characteristics and the normal state center in the bearing whole life process is obtained by calculating the Euclidean square distance and the membership function between the main characteristics and the normal state center respectively and is used as a degradation factor (DIs). Further calculated CVs over the life of the bearing are shown in fig. 8. It can be seen that the bearing performance degradation factor based on the multi-source signal shows good attenuation characteristics as a whole, and the CVs obtained based on the membership function shows better tendency than the CVs value obtained based on the euclidean square distance. And the CV value rise back is well represented as the response amplitude is reduced due to the occurrence of the locking fault in the last stage (after 1600 s). Fig. 9 shows the CVs value of the bearing in the whole life process, which is obtained by extracting the corresponding time domain and frequency domain characteristic values from the acceleration signal and then calculating the obtained value by using the membership function, and compared with fig. 8 b, the CVs value has very serious noise interference and no obvious trend.
Claims (3)
1. A performance degradation evaluation method for a micro turbine bearing based on multi-source information fusion is characterized by comprising the following steps:
step 1: establishing a characteristic sample set based on a bearing seat acceleration signal, a rotating shaft displacement signal and a temperature signal on a characteristic fusion level; the method comprises the following specific steps:
step 1.1: continuous sampling, collecting multi-source response signals including acceleration signal V of bearing during operation of bearing of microturbine b Rotation axis displacement signal V s And a bearing seat temperature signal T;
step 1.2: respectively extracting the characteristic parameters of the multi-source response signals in the step 1.1, and constructing an initial characteristic sample set W p*q ；
Step 1.3: normalizing the characteristic parameters in the step 1.2 by adopting a maximum and minimum normalization method, wherein the formula is as follows:
in the formula, w k For the k-th feature vector,
the corresponding normalized feature vectors are obtained;
step 1.4: obtaining a characteristic vector representing the running state of the bearing based on the dimensionality reduction treatment of PCA;
for normalized feature set
Introducing PCA (principal component analysis) to obtain a principal component PC (principal component analysis) of the feature set, namely the principal component with the highest variance, thereby constructing a feature vector f for representing the running state of the bearing PC And feature matrix F p*n ；
Step 2: constructing a state evaluation model based on k-center clustering
Step 2.1: feature vector f of normal state and failure state PC Introducing a k-medoids clustering algorithm to obtain a clustering center C at a normal stage and a failure stage Nor And C Fai ；
Step 2.2: respectively utilizing squared Euclidean distance and membership function to calculate rest state characteristic vector and C in bearing operation process Nor 、C Fai As a degradation factor DI characterizing the degradation of the bearing performance; the shorter the distance, the smaller the difference; thus, a larger distance indicates a more severe degradation of the bearing performance;
wherein, the expression for calculating DI by using squared Euclidean distance is as follows:
wherein h is less than n, h is the number of classifications, and n is the feature vector f PC The number of the cells;
is an arbitrary characteristic parameter; c. C i Is a clustering center;
the expression for DI is calculated using the membership functions as:
wherein r is 2; subscript D *A 2 norm representing the calculation vector, xy or ty;
for a brief and concise characterization of the bearing operation process, DI is further transformed into a confidence value CV between 0 and 1, as shown in equation (6):
CV＝exp(-DI/c) (6)
wherein c is a scale value; when the bearing fails, the CV value tends to 0.
2. The method of claim 1, wherein in step 1.2, an initial set of feature samples W is used p*q The method comprises the steps of obtaining a time-frequency domain characteristic parameter of an acceleration signal, a time domain characteristic parameter of a displacement signal and an average value of a temperature signal; in particular, a bearing acceleration signal V is extracted b Time domain characteristic parameter of (2): peak-to-peak, mean, root-mean-square, variance, standard deviation, kurtosis, form factor, peak factor, pulse factor, and margin factor; extracting bearing acceleration signal V b Frequency domain characteristic parameters of (1): inner ring rotation frequency f r And frequency f of passing of the rolling body on the outer ring bo Passing frequency f of rolling element in inner ring bi The revolution frequency f of the cage c Rolling element rotation frequency f b (ii) a Extracting a displacement signal V of a rotating shaft s Time domain characteristic parameter of (2): peak-to-peak, mean, root-mean-square, variance, standard deviation, kurtosis, form factor, peak factor, pulse factor, and margin factor; for the temperature signal T: and taking the average value of the temperatures of the three measuring points.
3. The evaluation method according to claim 1 or 2, wherein the step 1.4 is specifically as follows:
first, the covariance of the normalized feature vector is calculated:
wherein S is k Is normalized k-th feature vector
Covariance of (2), m k Is a correspondingAverage vector, T denotes matrix transpose;
then, S is obtained k The eigenvector corresponding to the largest eigenvalue is the first principal component, and so on for the remaining principal components.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210270292.5A CN114813119A (en) | 2022-03-18 | 2022-03-18 | Multi-source information fusion-based performance degradation evaluation method for miniature turbine bearing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210270292.5A CN114813119A (en) | 2022-03-18 | 2022-03-18 | Multi-source information fusion-based performance degradation evaluation method for miniature turbine bearing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114813119A true CN114813119A (en) | 2022-07-29 |
Family
ID=82530636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210270292.5A Pending CN114813119A (en) | 2022-03-18 | 2022-03-18 | Multi-source information fusion-based performance degradation evaluation method for miniature turbine bearing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114813119A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150048952A1 (en) * | 2011-12-21 | 2015-02-19 | Aktiebolaget Skf | Method of monitoring a health status of a bearing with a warning device in a percentage mode |
| CN108073158A (en) * | 2017-12-05 | 2018-05-25 | 上海电机学院 | Based on PCA and KNN density algorithm Wind turbines Method for Bearing Fault Diagnosis |
| JP2020056686A (en) * | 2018-10-02 | 2020-04-09 | 日本精工株式会社 | Abnormality diagnostic method and abnormality diagnostic device of rolling bearing, sensor unit, and abnormality diagnostic system of rolling bearing |
| CN111947928A (en) * | 2020-08-10 | 2020-11-17 | 山东大学 | Multi-source information fusion bearing fault prediction system and method |
| CN112330045A (en) * | 2020-09-02 | 2021-02-05 | 国网冀北电力有限公司承德供电公司 | Power transmission network line loss evaluation and reduction method based on K-medoids clustering analysis method |
| CN114046993A (en) * | 2021-10-19 | 2022-02-15 | 南京工业大学 | Slewing bearing state evaluation method based on multi-feature parameter fusion and FCM-HMM |
-
2022
- 2022-03-18 CN CN202210270292.5A patent/CN114813119A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150048952A1 (en) * | 2011-12-21 | 2015-02-19 | Aktiebolaget Skf | Method of monitoring a health status of a bearing with a warning device in a percentage mode |
| CN108073158A (en) * | 2017-12-05 | 2018-05-25 | 上海电机学院 | Based on PCA and KNN density algorithm Wind turbines Method for Bearing Fault Diagnosis |
| JP2020056686A (en) * | 2018-10-02 | 2020-04-09 | 日本精工株式会社 | Abnormality diagnostic method and abnormality diagnostic device of rolling bearing, sensor unit, and abnormality diagnostic system of rolling bearing |
| CN111947928A (en) * | 2020-08-10 | 2020-11-17 | 山东大学 | Multi-source information fusion bearing fault prediction system and method |
| CN112330045A (en) * | 2020-09-02 | 2021-02-05 | 国网冀北电力有限公司承德供电公司 | Power transmission network line loss evaluation and reduction method based on K-medoids clustering analysis method |
| CN114046993A (en) * | 2021-10-19 | 2022-02-15 | 南京工业大学 | Slewing bearing state evaluation method based on multi-feature parameter fusion and FCM-HMM |
Non-Patent Citations (2)
| Title |
|---|
| 古莹奎等: "基于主成分分析和支持向量机的滚动轴承故障特征融合分析", 《中国机械工程》 * |
| 张龙等: "基于Renyi熵和K-medoids聚类的轴承性能退化评估", 《振动与冲击》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Song et al. | Step-by-step fuzzy diagnosis method for equipment based on symptom extraction and trivalent logic fuzzy diagnosis theory | |
| Huo et al. | Incipient fault diagnosis of roller bearing using optimized wavelet transform based multi-speed vibration signatures | |
| CN111353482B (en) | LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method | |
| Harmouche et al. | Improved fault diagnosis of ball bearings based on the global spectrum of vibration signals | |
| Yu | Local and nonlocal preserving projection for bearing defect classification and performance assessment | |
| Kang et al. | A hybrid feature selection scheme for reducing diagnostic performance deterioration caused by outliers in data-driven diagnostics | |
| CN111120348A (en) | Centrifugal pump fault early warning method based on support vector machine probability density estimation | |
| Pan et al. | Robust bearing performance degradation assessment method based on improved wavelet packet–support vector data description | |
| Li et al. | Semisupervised distance-preserving self-organizing map for machine-defect detection and classification | |
| Shan et al. | A multisensor data fusion method for ball screw fault diagnosis based on convolutional neural network with selected channels | |
| Malhi et al. | PCA-based feature selection scheme for machine defect classification | |
| Yu | Bearing performance degradation assessment using locality preserving projections | |
| Soylemezoglu et al. | Mahalanobis-Taguchi system as a multi-sensor based decision making prognostics tool for centrifugal pump failures | |
| Yang et al. | Bearing fault automatic classification based on deep learning | |
| Kumbhar et al. | Theoretical and experimental studies to predict vibration responses of defects in spherical roller bearings using dimension theory | |
| Zhang et al. | A novel intelligent method for bearing fault diagnosis based on Hermitian scale-energy spectrum | |
| Lu et al. | Bearing health assessment based on chaotic characteristics | |
| Lu et al. | CEEMD-assisted bearing degradation assessment using tight clustering | |
| Almounajjed et al. | Investigation techniques for rolling bearing fault diagnosis using machine learning algorithms | |
| Çaliş et al. | Artificial immunity-based induction motor bearing fault diagnosis | |
| Fan et al. | A reinforced noise resistant correlation method for bearing condition monitoring | |
| Egaji et al. | A data mining based approach for electric motor anomaly detection applied on vibration data | |
| He et al. | The diagnosis of satellite flywheel bearing cage fault based on two-step clustering of multiple acoustic parameters | |
| Atta et al. | Detection and diagnosis of bearing faults under fixed and time-varying speed conditions using persistence spectrum and multi-scale structural similarity index | |
| CN114088389A (en) | Data processing method and related device for gearbox |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220729 |