CN118094182A - Data-based turntable bearing early fault online identification method - Google Patents
Data-based turntable bearing early fault online identification method Download PDFInfo
- Publication number
- CN118094182A CN118094182A CN202410162291.8A CN202410162291A CN118094182A CN 118094182 A CN118094182 A CN 118094182A CN 202410162291 A CN202410162291 A CN 202410162291A CN 118094182 A CN118094182 A CN 118094182A
- Authority
- CN
- China
- Prior art keywords
- turntable bearing
- data
- early
- signal
- fault
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000009467 reduction Effects 0.000 claims abstract description 26
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 25
- 230000008859 change Effects 0.000 claims abstract description 15
- 238000005457 optimization Methods 0.000 claims abstract description 8
- 238000012544 monitoring process Methods 0.000 claims abstract description 7
- 230000015556 catabolic process Effects 0.000 claims description 9
- 238000006731 degradation reaction Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 230000001186 cumulative effect Effects 0.000 claims description 4
- 230000000977 initiatory effect Effects 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 230000001629 suppression Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000036541 health Effects 0.000 abstract description 3
- 238000001914 filtration Methods 0.000 abstract description 2
- 238000000513 principal component analysis Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention provides a turntable bearing early fault online identification method based on data, and relates to the technical field of turntable bearing health monitoring. Firstly, acquiring online vibration signal monitoring data of a turntable bearing; then decomposing the vibration signal into a plurality of Product Functions (PF) by utilizing self-adaptive complete robust mean decomposition (CERLMDAN), optimizing decomposition parameters by utilizing a parameter optimization algorithm, and adopting Kernel Principal Component Analysis (KPCA) to select fault PF for reconstruction so as to achieve the purpose of filtering and denoising; and then, carrying out data reduction on the vibration signals, carrying out neighborhood correlation graph ellipse fitting on the reduced vibration signals, and using the change of the inclination angle of the ellipse as a discrimination index of early faults to realize the online identification of the early faults of the turntable bearing. The method provides a new solution for early fault identification of large-scale low-speed rotating machinery, and is widely applied to the field of mechanical equipment identification.
Description
Technical Field
The invention belongs to the technical field of health monitoring of turntable bearings, and relates to an early fault online identification method of turntable bearings based on data.
Background
The turntable bearing is used as a low-speed heavy-load bearing and is gradually popularized and applied in the fields of large-scale wind driven generators, shield machines, ocean platforms and the like in recent years. The damage to the turntable bearing is difficult to avoid due to the severe working condition environment and the complex stress mode, and once the turntable bearing fails, the whole machine is stopped, and even serious safety accidents are caused. Therefore, early fault identification becomes a difficulty in health monitoring research of a large-scale low-speed turntable bearing, and how to accurately perform non-stationary signal noise reduction is a research basis of early fault identification.
On one hand, EEMD does not consider reconstruction errors, and PCA discards high-order nonlinear statistic information; on the other hand, PCA is carried out on components decomposed by EEMD, components with larger difference between SPE mean value and threshold value are selected as fault characteristic components, and then common fault characteristic components decomposed in different life stages are selected to reconstruct signals so as to achieve the purpose of noise reduction.
In addition, the existing fault diagnosis method based on the signal processing technology is used for judging whether a fault occurs or not by analyzing fault vibration characteristics of complex components or systems and extracting vibration signal characteristic information by means of the signal processing technology. When the rolling body or the roller path of the turntable bearing breaks down, pulse vibration is caused, but the early fault characteristic information is weak, and the prior signal processing technology captures the fault characteristic frequency of the turntable bearing by frequency domain, time-frequency domain and other methods, so that the early fault identification of the turntable bearing is difficult.
Therefore, the early fault on-line identification of the turntable bearing is realized, the decomposition reconstruction error is required to be fully researched and reduced by CERLMDAN, the decomposition precision is improved, the nonlinear high-order statistical information is captured by adopting KPCA, the weighted accumulated value of the decomposition component in the whole life cycle is taken as a selection parameter, the overall variation trend of each component is highlighted, and finally the neighborhood related ellipse inclination angle direction is taken as a fault discrimination index, so that the early fault identification of the turntable bearing is finally realized.
Disclosure of Invention
The invention aims to provide a data-based online identification method for early faults of a turntable bearing, which fully utilizes the signal noise reduction capability of CERLMDAN-KPCA and the neighborhood related early fault identification capability to solve the problems that the low-frequency fault characteristic information of the turntable bearing is weak, and particularly the low-frequency fault component of the early signal is difficult to extract and difficult to identify.
The invention adopts the following technical scheme:
The invention provides a data-based early fault online identification method for a turntable bearing, which comprises the steps of firstly acquiring online vibration signal monitoring data of the turntable bearing; then decomposing the vibration signal into a plurality of Product Functions (PF) by utilizing self-adaptive complete robust mean decomposition (CERLMDAN), optimizing decomposition parameters by utilizing a parameter optimization algorithm, and adopting Kernel Principal Component Analysis (KPCA) to select fault PF for reconstruction so as to achieve the purpose of filtering and denoising; then, data reduction is carried out on the vibration signals, neighborhood correlation graph ellipse fitting is carried out on the reduced vibration signals, and the early failure on-line identification of the turntable bearing is realized by taking the change of the inclination angle of the ellipse as the identification index of the early failure, and the specific implementation steps are as follows:
acquiring an operation vibration signal, acquiring a turntable bearing vibration signal by using a vibration sensor, and storing historical operation data and online operation data of the vibration sensor;
the signal decomposition based on CERLMDAN is used for decomposing a vibration signal into N sections, and then each section of signal is decomposed by CERLMDAN to obtain an H-order PF component;
the CERLMDAN parameter optimization method is used for optimizing the super parameters in CERLMDAN decomposition;
the abnormal component selection based on KPCA splits the h (h E [1, H ]) order PF in the PF component of the first segment signal decomposition into a multidimensional matrix G 1h, simultaneously splits the h order PF in the PF matrix of the n (n E [1, N ]) segment on-line operation into a multidimensional matrix G nh, carries out KPCA on G 1h and G nh, obtains the square prediction error SPE nh of on-line operation data G nh by taking G 1h as a basic sample, calculates the root mean square value R nh and subtracts R 1h to obtain the difference S nh, finally calculates the weighted cumulative value WCV h which can reflect the degradation trend of PF in the operation period, and has the calculation formula as follows It should be noted that since the high frequency PF component is uniform in any period, WCV thereof is small; the low-frequency PF component is characterized by obvious change in different degradation stages along with the occurrence and aggravation of faults, so that the larger WCV is, the better the PF of the stage can reflect the degradation trend of the turntable bearing.
The KPCA-based signal reconstruction is used for selecting fault components and performing signal reconstruction so as to achieve the purpose of noise reduction. When the ratio of the sum of j (j e [1, H ]) PFs with the maximum WCV h to the sum of all WCV h sums exceeds alpha, the j PFs are used as the reconstruction components of the running vibration signals and are accumulated, so that the final noise reduction reconstruction signals can be obtained.
The vibration signal time sequence is subjected to dimension reduction, and the original time sequence of the vibration signal is converted, so that the purpose of representing the original time sequence in a low dimension is achieved, and the original characteristics of the signal are maintained. It should be noted that the sampling rate of the vibration signal in the on-line monitoring system is usually set above several khz to meet the broadband sampling requirement, but for the low-speed turntable bearing, the huge data volume caused by the high sampling rate must increase the calculation burden of early failure recognition.
And the neighborhood related ellipse fitting is used for carrying out neighborhood related graph visual representation on the reduced data and fitting by a discrete point ellipse fitting method.
And the early fault identification is used for judging the fault impact change condition of the turntable bearing by fitting the inclination direction of the ellipse in the coordinates, so as to identify the early fault state of the turntable bearing. It should be noted that the normal operation signal of the turntable bearing mainly includes high-frequency noise, but with the occurrence of an early failure, the frequency characteristic of the high-frequency main component is shifted to the low-frequency main component. Therefore, the early failure of the turntable bearing can be reflected by capturing the change of frequency in the vibration signal in the elliptical tilt direction.
2. The online identification method of early failure of a turntable bearing based on data according to claim 1, wherein the CERLMDAN parameter optimization method is determined as follows:
Optimizing the super parameters in CERLMDAN models by adopting a moth fire suppression algorithm (MFO); the super-parameters comprise noise amplitude coefficients and integration times.
3. The online identification method for early failure of a turntable bearing based on data according to claim 1, wherein the vibration signal time sequence is subjected to dimension reduction, the time sequence is subjected to dimension reduction by adopting a piecewise cumulative approximation (PAA), the time sequence is subjected to average segmentation, the segmentation information is reflected by the segmentation average value, and finally the purpose of dimension reduction of the data is achieved, wherein the calculation formula is as followsWhere x= (x 1,x2,…,xL) is L data sample sequences, w is the data amount of each segment of the sequence, and then dividing the sample sequence x into M segments equally, where m=l/w, and y= (y 1,y2,…,yM) is the new sequence after reduction.
4. The online identification method for early failure of a turntable bearing based on data according to claim 3, wherein the neighborhood correlation map is subjected to ellipse fitting, discrete points in the neighborhood correlation map are fitted by adopting a direct ellipse fitting method, wherein each point has an abscissa of y m and an ordinate of y m+1,
5. The online identification method of early failure of a turntable bearing based on data according to claim 4, wherein the early failure identification is performed by extracting a full-period noise reduction signal of one rotation of the turntable bearing, performing PAA data reduction and ellipse fitting, and indicating the occurrence of early failure if an ellipse inclination change occurs therein.
Compared with the prior art, the invention has the following advantages:
1. The traditional multi-scale self-adaptive decomposition method has the problems of end-point effect, modal aliasing and the like, and the problem of the complaint can be effectively solved by adding white noise into a signal, but a reconstruction error cannot be avoided. According to the method, CERLMDAN is utilized, white noise is adaptively added in each stage of robust local mean decomposition, and multi-scale components are obtained through integrated averaging, so that the problems of modal aliasing, reconstruction errors and the like existing in the traditional method are effectively solved. In addition, the greatest problem of noise-assisted adaptive decomposition is that key parameters of the self-adaptive decomposition need to be set manually, and decomposition parameters (such as noise amplitude coefficients and integration times) have great influence on the decomposition effect, and the existing method is often selected in an empirical mode, but has no universality. The method adopts the moth fire suppression algorithm to adaptively optimize the decomposition parameters, has the performance characteristics of strong parallel optimization capability, good global property and difficult falling into local extremum, and improves the signal decomposition precision.
2. The traditional PCA discards the high-order statistic information, and the method can make up the defect in the aspect by adopting KPCA, thereby effectively improving the nonlinear processing capability. The existing fault component extraction method after self-adaptive decomposition mainly screens fault components by calculating the characteristics of the components or comparing the components with the original signals, however, the rotating speed of the turntable bearing is lower, the low-frequency fault characteristic information is weak, and particularly, the low-frequency fault components of early signals are not easy to extract. The method fully considers the uniformity of the high-frequency component in any period, and the characteristic that the low-frequency component presents obvious change in different degradation stages along with the occurrence and aggravation of faults, and considers that the degradation trend of the multi-scale component in the whole life cycle is measured, and finally the effective component is extracted according to the degradation trend, so that the accuracy of extracting the low-frequency fault component is improved.
3. When the rolling body or the rollaway nest of the turntable bearing breaks down, pulse vibration is caused, and the existing signal processing technology mainly judges whether equipment breaks down or not by identifying the characteristic frequency of the fault, so that the signal processing method is more suitable for processing the vibration signals of the turntable bearing with serious faults in the later life or artificially generated. The normal operation signal of the turntable bearing mainly comprises high-frequency noise, but with the initiation of early faults, the frequency characteristic of the high-frequency main component is changed into the low-frequency main component. The method researches a neighborhood related identification method, and identifies early faults of the turntable bearing by capturing the change from high frequency to low frequency in the vibration signal.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a flowchart provided in an embodiment of the present invention.
FIG. 2 is a diagram illustrating a CERLMDAN-KPCA configuration according to an embodiment of the present invention.
Fig. 3 is a diagram for reducing noise of a full-life vibration signal of a turntable bearing according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of early fault detection of a turntable bearing according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, the online identification method for the service life state of the turntable bearing based on data provided by the embodiment of the invention comprises the following steps:
Step 1: an operational vibration signal is acquired. In the example, a group of vibration signals obtained by a 11-day fatigue life test of the turntable bearing are adopted, the running rotating speed of the turntable bearing is 4r/min, a vibration sensor is used for collecting the vibration signals of the turntable bearing, and the whole life running data of the vibration sensor are stored;
step 2: MFO-CERLMDAN signal decomposition. Decomposing the whole life operation data into N sections, decomposing each section of data by using MFO-CERLMDAN, decomposing each section of signal to obtain 7-order PF components as shown in figure 2, and splitting the 7-order PF components into a multidimensional matrix G;
Step 3: and selecting KPCA abnormal components. The h (h E [1,7 ]) order PF in PF components of the first section of signal decomposition is split into a multidimensional matrix G 1h, meanwhile, the h order PF in PF matrixes of the n (n E [1, N ]) section of operation data is split into a multidimensional matrix G nh, the G 1h and the G nh are subjected to KPCA to obtain square prediction error SPE nh of the operation data, a root mean square value R nh of the square prediction error is calculated and subtracted from the R 1h to obtain a difference value S nh, and finally a weighted accumulated value WCV h is calculated.
Step 4: and (5) reconstructing a signal. When the ratio of the sum of the total sum of all WCV h of the maximum j (j e 1, 7) PFs of WCV h exceeds α, the present example selects the 3 rd, 4 th, 5 th, 6 th and 7 th PFs as the reconstruction components of the operating vibration signal, and performs accumulation, so as to obtain the final noise reduction reconstruction signal, as shown in fig. 3. As can be seen from FIG. 3, the noise signal is greatly removed after CERLMDAN-KPCA treatment of the turntable bearing life-cycle vibration signal, and the fault characteristics are clearer.
Step 5: the vibration signal time sequence reduces the dimension. The full period noise reduction signal, namely the 15s data size, of one revolution of the turntable bearing is extracted and subjected to PAA data reduction.
Step 6: and (5) fitting a neighborhood-related ellipse. And carrying out visual representation on the neighborhood correlation diagram on the reduced data, wherein the abscissa of each point is y m, the ordinate is y m+1, and fitting discrete points in the neighborhood correlation diagram by a direct ellipse fitting method.
Step 7: early fault identification. Judging the fault impact change condition of the turntable bearing by fitting the inclination direction of the ellipse in the coordinates, if the inclination angle of the ellipse changes, indicating that early faults occur, as shown in fig. 4, from the 1 st to 5 th days of the test, the normal operation signal of the turntable bearing mainly takes high-frequency noise as a main part, the fitted ellipse is inclined to the left, and the inclination angle of the ellipse does not change; when the test is carried out until the 6 th day, namely along with the initiation of early faults, the frequency characteristic of the high-frequency main component is changed into the low-frequency main component, the fitted ellipse is inclined to the right, and the inclination angle of the ellipse is changed at the moment; and on the 7 th to 11 th days of the test, the operation signal of the turntable bearing mainly comprises a low-frequency fault component, the fitted ellipse is right inclined, and the inclination angle of the ellipse is unchanged. Comprehensive life test analysis shows that when the test is carried out on the 7 th day, fatigue fracture of one bolt occurs, and then the machine disassembly and inspection are carried out, so that the outer ring raceway of the turntable bearing shows small area slippage, and early failure is indicated. Therefore, the early failure of the turntable bearing can be accurately identified by fitting the change of the elliptical inclination angle direction, and the established early failure identification method can be used for on-line identification of the early failure of the turntable bearing of the same type.
The principles and embodiments of the present invention have been described in detail with reference to specific examples, which are provided to facilitate understanding of the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (5)
1. An online identification method for early faults of a turntable bearing based on data is characterized by comprising the following steps: acquiring an operation vibration signal; signal decomposition based on CERLMDAN; CERLMDAN parameter optimization method; selecting and reconstructing abnormal components based on KPCA; reducing the dimension of the vibration signal time sequence; elliptical fitting of the neighborhood correlation diagram; and early fault identification, which mainly comprises the following steps of;
acquiring an operation vibration signal, acquiring a turntable bearing vibration signal by using a vibration sensor, and storing historical operation data and online operation data of the vibration sensor;
the signal decomposition based on CERLMDAN is used for decomposing a vibration signal into N sections, and then each section of signal is decomposed by CERLMDAN to obtain an H-order PF component;
the CERLMDAN parameter optimization method is used for optimizing the super parameters in CERLMDAN decomposition;
the abnormal component selection based on KPCA splits the h (h E [1, H ]) order PF in the PF component of the first segment signal decomposition into a multidimensional matrix G 1h, simultaneously splits the h order PF in the PF matrix of the n (n E [1, N ]) segment on-line operation into a multidimensional matrix G nh, carries out KPCA on G 1h and G nh, obtains the square prediction error SPE nh of on-line operation data G nh by taking G 1h as a basic sample, calculates the root mean square value R nh and subtracts R 1h to obtain the difference S nh, finally calculates the weighted cumulative value WCV h which can reflect the degradation trend of PF in the operation period, and has the calculation formula as follows It should be noted that since the high frequency PF component is uniform in any period, WCV thereof is small; the low-frequency PF component presents the characteristic of obvious change in different degradation stages along with the occurrence and aggravation of faults, so that the larger WCV is, the better the PF of the stage can reflect the degradation trend of the turntable bearing performance;
the KPCA-based signal reconstruction is used for selecting fault components and performing signal reconstruction so as to achieve the purpose of noise reduction. Setting the weight as alpha (alpha epsilon (0, 1)), and when the proportion of the sum of the total sum of the j (j epsilon [1, H ]) PFs with the maximum WCV h to the sum of all WCV h total sums exceeds alpha, the j PFs are used as the reconstruction components of the running vibration signals and are accumulated, so that the final noise reduction reconstruction signals can be obtained;
The vibration signal time sequence dimension reduction is realized by converting the original time sequence of the vibration signal so as to achieve the purpose of representing the original time sequence in a low dimension and retain the original characteristics of the signal, and the fact that the sampling rate of the vibration signal in an online monitoring system is usually set to be more than a few kilohertz to meet the broadband sampling requirement is pointed out, but for a low-speed turntable bearing, the huge data volume caused by the high sampling rate must increase the calculation burden of early fault identification;
The neighborhood correlation ellipse fitting is used for carrying out neighborhood correlation graph visual representation on the reduced data and fitting through a discrete point ellipse fitting method;
The early fault identification judges the impact change condition of the fault of the turntable bearing by fitting the inclination direction of the ellipse in the coordinates, and further identifies the early fault state of the turntable bearing, and the early fault identification is characterized in that the normal operation signal of the turntable bearing mainly comprises high-frequency noise, but along with the initiation of the early fault, the frequency characteristic of the high-frequency main component is converted into the low-frequency main component, so that the early fault of the turntable bearing can be reflected by capturing the change of the frequency in the vibration signal through the inclination direction of the ellipse.
2. The online identification method of early failure of a turntable bearing based on data according to claim 1, wherein the CERLMDAN parameter optimization method is determined as follows:
Optimizing the super parameters in CERLMDAN models by adopting a moth fire suppression algorithm (MFO); the super-parameters comprise noise amplitude coefficients and integration times.
3. The online identification method for early failure of a turntable bearing based on data according to claim 1, wherein the vibration signal time sequence is subjected to dimension reduction, the time sequence is subjected to dimension reduction by adopting a piecewise cumulative approximation (PAA), the time sequence is subjected to average segmentation, the segmentation information is reflected by the segmentation average value, and finally the purpose of dimension reduction of the data is achieved, wherein the calculation formula is as followsWhere x= (x 1,x2,…,xL) is L data sample sequences, w is the data amount of each segment of the sequence, and then dividing the sample sequence x into M segments equally, where m=l/w, and y= (y 1,y2,…,yM) is the new sequence after reduction.
4. The online identification method for early failure of turntable bearing based on data as claimed in claim 3, wherein the neighborhood correlation map is elliptic fitted, and discrete points in the neighborhood correlation map are fitted by adopting a direct elliptic fitting method, wherein each point has an abscissa of y m and an ordinate of y m+1.
5. The online identification method of early failure of a turntable bearing based on data according to claim 4, wherein the early failure identification is performed by extracting a full-period noise reduction signal of one rotation of the turntable bearing, performing PAA data reduction and ellipse fitting, and indicating the occurrence of early failure if an ellipse inclination change occurs therein.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410162291.8A CN118094182A (en) | 2024-02-05 | 2024-02-05 | Data-based turntable bearing early fault online identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410162291.8A CN118094182A (en) | 2024-02-05 | 2024-02-05 | Data-based turntable bearing early fault online identification method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN118094182A true CN118094182A (en) | 2024-05-28 |
Family
ID=91151058
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410162291.8A Pending CN118094182A (en) | 2024-02-05 | 2024-02-05 | Data-based turntable bearing early fault online identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118094182A (en) |
-
2024
- 2024-02-05 CN CN202410162291.8A patent/CN118094182A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yin et al. | Weak fault feature extraction of rolling bearings based on improved ensemble noise-reconstructed EMD and adaptive threshold denoising | |
CN108760327B (en) | Diagnosis method for rotor fault of aircraft engine | |
CN111089726B (en) | Rolling bearing fault diagnosis method based on optimal dimension singular spectrum decomposition | |
CN108181105B (en) | Rolling bearing fault pre-diagnosis method and system based on logistic regression and J divergence | |
CN113375940A (en) | Fault bearing diagnosis method based on SVD and CEEMDAN | |
CN111170103B (en) | Equipment fault identification method | |
CN110160765A (en) | A kind of shock characteristic recognition methods and system based on sound or vibration signal | |
CN114112400A (en) | Mechanical bearing fault diagnosis method based on multi-angle information fusion | |
CN112182912B (en) | Manufacturing equipment spindle bearing health assessment method based on probability description and spectrum analysis | |
CN115034137A (en) | RVM and degradation model-based two-stage hybrid prediction method for residual life of bearing | |
CN114266197A (en) | Method for diagnosing equipment fault of hydropower station | |
CN113607415A (en) | Bearing fault diagnosis method based on short-time stochastic resonance under variable rotating speed | |
CN110987433B (en) | Bearing fault early warning method based on high-frequency signal characteristic amplitude | |
CN115060491A (en) | Fan bearing operation health degree assessment method and system based on multi-source data | |
CN114486263B (en) | Noise reduction demodulation method for vibration signal of rolling bearing of rotary machine | |
CN115424635A (en) | Cement plant equipment fault diagnosis method based on sound characteristics | |
CN116308300A (en) | Power equipment state monitoring evaluation and command method and system | |
CN117093938A (en) | Fan bearing fault detection method and system based on deep learning | |
CN112683533A (en) | Signal enhancement method and system for bearing fault diagnosis | |
CN118094182A (en) | Data-based turntable bearing early fault online identification method | |
CN109446625B (en) | Bayesian inference-based helicopter maneuvering component dynamic threshold calculation method | |
TWI398629B (en) | Equipment supervision method | |
CN115114955B (en) | Equipment fault detection method based on sound and vibration signals | |
CN117723303B (en) | Acoustic monitoring method for wind generating set bearing | |
KR101967629B1 (en) | Signal Data Processing Apparatus For Prediction And Diagnosis Of Nuclear Power Plant |
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 |