CN111504647A - AR-MSET-based performance degradation evaluation method for rolling bearing - Google Patents
AR-MSET-based performance degradation evaluation method for rolling bearing Download PDFInfo
- Publication number
- CN111504647A CN111504647A CN202010516225.8A CN202010516225A CN111504647A CN 111504647 A CN111504647 A CN 111504647A CN 202010516225 A CN202010516225 A CN 202010516225A CN 111504647 A CN111504647 A CN 111504647A
- Authority
- CN
- China
- Prior art keywords
- model
- mset
- performance degradation
- rolling bearing
- 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
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
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Acoustics & Sound (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a performance degradation evaluation method of a rolling bearing based on AR-MSET. Firstly, extracting vibration signal characteristics of a rolling bearing in a normal running state by using an autoregressive timing model (AR), constructing a historical memory matrix of a Multivariate State Estimation (MSET) model by using a faultless AR model coefficient, inputting the AR coefficient of a signal to be measured into the MSET model as an observation vector, performing optimal reconstruction estimation to obtain an estimation vector, respectively substituting the observation vector and the estimation vector into the AR model of the signal to be measured to obtain respective residual sequences, obtaining the Difference (DR) between the root mean square values of the residual sequences of the observation vector and the estimation vector, and simultaneously setting an adaptive pre-alarm threshold.
Description
Technical Field
The invention relates to an AR-MSET-based rolling bearing performance degradation evaluation method, and belongs to the technical field of mechanical product quality reliability evaluation and fault diagnosis.
Background
The performance of a rolling bearing, which is one of the key components of a rotating machine, directly determines the performance of the machine. Once a fault occurs, the normal safe operation of mechanical equipment is directly influenced, and even serious safety accidents are caused. Therefore, the method has great significance on the in-service state detection and performance degradation evaluation of the rolling bearing. Reducing the cost of down time and achieving near zero down time are the ultimate goals of pre-diagnostics. However, without accurate prediction of remaining useful life before an actual failure, it is not possible to achieve all the advantages of pre-diagnosis. Inaccurate predictive information may lead to unnecessary maintenance, such as early replacement of components, etc. Therefore, the accuracy of the prediction of the residual service life plays a crucial role in fully realizing the potential of predicted maintenance.
Proper state feature extraction of the signals of the equipment is a prerequisite for fault diagnosis and prediction. The vibration signal is widely used because of its advantages of large information amount and easy collection. Common device state feature extraction based on vibration signals can be classified into time domain statistical analysis (root mean square value, kurtosis, skewness), frequency domain analysis (amplitude spectrum analysis, cepstrum analysis), time-frequency domain analysis (quadratic time-frequency distribution, wavelet analysis), time sequence model analysis (autoregressive moving average model, autoregressive time sequence model), and the like. Among them, the time-series model analysis method, especially the Autoregressive (AR) model analysis method, has model parameters that have the capability of representing the system state and have high sensitivity to the state change of the system, and thus is widely applied in the field of fault diagnosis. Early failure identification of the rolling bearing is realized by combining an AR model and spectral kurtosis from flying clouds and the like. Cheng et al, using EMD as a signal preprocessing method before AR model generation, combine the obtained IMF-AR model with a support vector machine, and the result shows that the gear state can be accurately identified under the condition of a small amount of samples.
The essence of the performance degradation assessment is to perform similarity measurement between the sample signal to be measured and the fault-free reference model. In recent years, performance degradation evaluation Models of some probability similarities are proposed in succession, such as Hidden Markov Models (HMMs), Gaussian Mixed Models (GMMs), and the like. The core based on the probabilistic similarity evaluation Model is to establish a density Model under a fault-free condition and detect abnormality according to the density Model, for example, a Quaternary cloud and the like acquire the optimal degradation state number of equipment through a Dirichlet Process Mixed Model (DPMM), establish a Continuous Hidden Markov Model (CHMM) of the equipment, and take the probability value of an observer belonging to the CHMM as a bearing performance degradation value. The performance degradation estimation is carried out on the bearing by utilizing the wavelet packet entropy and the GMM model in Liweihua and the like, and the result shows that the method can effectively reflect the performance degradation process of the bearing in the whole life cycle.
The probability similarity evaluation model based on feature extraction expects deep information mining on corresponding data through a proper signal processing method to improve the sensitivity, consistency and the like of features on fault degree, but in practical application, the problems of complex ① calculation, complex training and testing processes of GMM, HMM and the like and premature saturation phenomenon ② exist, and when the probability evaluation model method such as HMM shows that the similarity between a sample to be tested and a fault-free reference model is zero, the condition that equipment does not completely enter a real failure state exists, namely a model limit value is earlier than a real failure value.
The core of the performance degradation evaluation model based on reconstruction is to reconstruct data to be measured through a fault-free reference model and measure the performance degradation degree by using the difference of the reconstructed data to be measured. And e.g. Hui, training the self-organizing mapping neural network by using normal sample data, and quantifying the fault degree of the bearing according to the deviation degree of the sample to be tested and the fault-free reference model. The reconstruction model quantifies the fault degree of the test data through reconstruction deviation (such as Euclidean distance), and the phenomenon of premature saturation of the probability similarity evaluation model is effectively avoided.
Based on the method, the invention provides an AR-MSET-based online evaluation method for performance degradation of a rolling bearing. The vibration signal of the rolling bearing is widely adopted due to the advantages of large information amount, easy acquisition and the like, and the initial fault sample can be analyzed by an envelope spectrum analysis method based on adaptive frequency band filtering and envelope demodulation.
Disclosure of Invention
The invention aims to provide an AR-MSET-based rolling bearing performance degradation online evaluation method, so that in-service state monitoring and performance degradation evaluation of a rolling bearing are realized, the downtime cost is reduced, and major sudden failures are prevented.
The performance degradation online evaluation method of the rolling bearing of the AR-MSET comprises the following specific steps:
(1) extracting characteristics: establishing an AR model by using a fault-free data sample and a data sample to be measured, respectively obtaining a fault-free sample AR model coefficient and a sample AR model coefficient to be measured, taking the fault-free sample AR model coefficient as a historical observation vector, and taking the sample AR model coefficient to be measured as an observation vectorX obs。
(2) Establishing a model: and taking the coefficients of the fault-free sample AR model as historical observation vectors of the MSET model, constructing a historical memory matrix, and establishing the MSET model.
(3) And (3) real-time evaluation: taking the AR model coefficient of the sample to be measured as an observation vectorX obsInputting the data into a MSET model to obtain a reconstructed AR model coefficient, namely an estimated vectorX estWill estimate the vectorX estAnd the observation vectorX obsAnd respectively substituting the residual sequences into an AR model of a sample signal to be detected, and obtaining respective residual sequences through time sequence modeling, so as to obtain the root mean square value Difference (DR) of the two residual sequences of the performance degradation index, and drawing a performance degradation curve of the rolling bearing.
Preferably, the specific content of the extracted features is as follows:
(a) establishing an AR model by using the first 100 groups of non-fault samples and the 982 groups of samples to be tested in the whole life cycle;
(b) and extracting autoregressive coefficients and residual errors of the AR model, determining the order of the AR model to be 30 according to a BIC (building information center) criterion, taking the autoregressive coefficients of the first 100 groups of fault-free samples as historical observation vectors, and taking the autoregressive coefficients of 982 groups of samples to be measured in the full life cycle as the observation vectors input into the MSET model.
Preferably, the specific content of the modeling is as follows:
and (3) using the autoregressive coefficients of the first 100 groups of fault-free samples as historical observation vectors to construct a historical memory matrix and establish an MEST model.
Preferably, the real-time evaluation comprises the following specific contents:
after the MSET model is established, auto-regression coefficients of 982 groups of samples to be measured in the full life cycle are taken as observation vectors and sequentially input into the MSET model to obtain observation vectors (namely reconstructed auto-regression coefficients), the observation vectors are substituted into the AR model of the original sample signal to be measured, a reconstructed residual sequence can be obtained through time sequence modeling, finally, the difference value of the RMS of the reconstructed residual sequence and the RMS of the original signal to be measured residual sequence is calculated, so that the DR index of the fault degree can be obtained, and a performance degradation curve is drawn.
The result verification of the rolling bearing performance degradation evaluation method based on the multivariate state estimation model is characterized by comprising the following steps of:
(a) determining the performance degradation starting time of the rolling bearing by using a 3 sigma criterion in statistics, and when the DR value of continuous 3 samples to be measured exceeds an early warning threshold value T (te) at the time of te, determining that the performance of the rolling bearing is changed;
(b) the kurtosis is used as a fault degree index of a bearing full-life fatigue test, comparative analysis is carried out, and the superiority of the bearing full-life fatigue test is verified;
(c) verifying the reliability of the obtained performance degradation curve by using a bearing accelerated fatigue test;
(d) and verifying the correctness of the evaluation result after analyzing the sample signal to be tested by using an envelope spectrum analysis method based on adaptive frequency band filtering and envelope demodulation.
Has the advantages that:
according to the characteristics of vibration signals in the process of bearing performance degradation, 100 groups of data in a normal state and 982 groups of sample data to be measured in a full life cycle are respectively subjected to characteristic extraction, an AR model is built, AR model coefficients of two types of samples are obtained, the AR model coefficients of the samples in the normal state are used as historical observation vectors, a historical memory matrix is built, and an MSET model is built. The method comprises the steps of inputting an AR model coefficient of a sample to be detected into an MSET model as an observation vector Xobs to obtain a reconstructed AR model coefficient, namely an estimated vector Xest, inputting the reconstructed AR model coefficient obtained through AR and MSET and the AR model coefficient of the sample to be detected into the AR model of the sample to be detected to obtain a reconstructed residual sequence, and calculating the difference value between the RMS of the reconstructed residual sequence and the RMS of the original signal to be detected residual sequence to obtain a fault degree DR index.
(1) The autoregressive coefficient of the AR model is used as an input feature, and the AR model is used for extracting the feature of the rolling bearing vibration signal, so that the data dimension can be effectively reduced;
(2) inputting the reconstructed AR model coefficient obtained by AR and MSET and the AR model coefficient of the sample to be detected into the AR model of the sample to be detected to obtain a reconstructed residual sequence, and calculating the difference value between the RMS of the reconstructed residual sequence and the RMS of the original signal to be detected residual sequence to obtain a fault degree DR index, wherein the DR index combines the advantages of the two indexes, has the capacity of representing the fault degree, can find early faults of the bearing in time, and can accurately reflect each stage of the performance degradation of the rolling bearing;
(3) the performance degradation curve described by the performance degradation evaluation method of the rolling bearing based on the AR-MSET has the consistency advantage with the degradation trend;
(4) the rolling bearing performance degradation evaluation method based on the AR-MSET has the most prominent advantages that the method does not need full life cycle data and can realize online real-time monitoring and evaluation.
Drawings
FIG. 1 is a flowchart of evaluation of the degree of failure of a rolling bearing;
FIG. 2 is a kurtosis index performance degradation evaluation curve;
FIG. 3 shows the results of AR-MSET performance degradation evaluation;
fig. 4 is an envelope demodulation diagram of No.536 samples.
Detailed Description
The invention is further illustrated by the following detailed description in conjunction with the accompanying drawings:
test sample data of the embodiment is provided by an intelligent maintenance center of the university of Cincinnati, the total service life cycle acquires 984 data files, and finally, serious outer ring faults occur in the bearing, so that bearing vibration signals of last 2 groups of abnormal bearings are removed.
Example 1:
as shown in fig. 1, which is an evaluation flowchart of the present invention, the performance degradation evaluation method of a rolling bearing of a basic AR-MSET specifically includes the following steps:
(1) extracting characteristics: the method comprises the steps of establishing an AR model by using the first 100 groups of non-fault samples and the 982 groups of samples to be tested in the full life cycle, extracting autoregressive coefficients and residual errors by using the AR model, determining the order of the AR model to be 20 according to a BIC criterion, using the autoregressive coefficients of the first 100 groups of non-fault samples as historical observation vectors, and using the autoregressive coefficients of the 982 groups of samples to be tested in the full life cycle as observation vectors input into an MSET model.
(2) Establishing a model: and (3) taking the AR model coefficients of the first 100 groups of fault-free data samples as historical observation vectors, and constructing a historical memory matrix of the MSET model according to the historical observation vectors.
(3) And (4) evaluation results: and sequentially inputting autoregressive coefficients of 982 groups of samples to be detected in the full life cycle as observation vectors into an MSET (modeling robust features) model to obtain observation vectors (namely autoregressive coefficients after reconstruction), substituting the observation vectors into an AR (augmented reality) model of original signals of the samples to be detected, obtaining a residual sequence after reconstruction through time sequence modeling, and finally calculating the difference value of the RMS of the residual sequence after reconstruction and the RMS of the residual sequence of the original signals to be detected to obtain a fault degree DR index and draw a performance degradation curve.
It can be seen from fig. 2 that the result obtained by using kurtosis as the indicator of the degree of failure is that the kurtosis value at 3 consecutive time instants after the 646 th sample is greater than or equal to the adaptive alarm threshold, and the 646 th sample can be considered as the initial failure time instant.
It can be seen from fig. 3 that by using the AR-MSET evaluation method, after the 536 th sample, the DR value of the test sample at 3 consecutive times is greater than or equal to the adaptive pre-warning threshold, which indicates that the observation vector at that time has begun to deviate from the history memory matrix, and the bearing begins to have an early failure. The consistency of the performance degradation trend and the degradation curve is better than that of the former method, the 696 th sample reaches a moderate fault degree, and a process of 'fault smoothing-redecoration' occurs, so that the curve fluctuates back and forth, the curve rises sharply at the 902 th sample, and the bearing performance is deteriorated sharply.
(4) And (4) verifying the evaluation result: in order to verify the correctness of the evaluation result of the 536 th sample when the initial fault occurs, the original signal of the 536 th sample data is subjected to adaptive frequency band filtering by using the peak factor of the envelope spectrum as an optimization index, and then the obtained filtered signal is subjected to envelope spectrum analysis, and the result is shown in fig. 4. As can be seen from fig. 4, after filtering, noise components in the vibration signal are reduced, a relatively obvious pulse phenomenon appears in a time domain diagram, and a first-frequency doubling 230.5Hz and a second-frequency doubling 460.9 Hz third-frequency doubling 691.4Hz which are close to the outer ring fault frequency appear in an envelope spectrum, so that the outer ring fault of the bearing at this moment can be considered, and the analysis result is consistent with the previous evaluation result.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made in the above embodiments by those of ordinary skill in the art without departing from the principle and spirit of the present invention.
Claims (5)
1. The performance degradation evaluation method of the rolling bearing based on the AR-MSET is characterized by comprising the following specific steps of:
(1) extracting characteristics: establishing an AR model by using a fault-free data sample and a data sample to be measured, determining the order of the AR model by using the BIC criterion, taking the fault-free sample AR model coefficient as a historical observation vector, and taking the sample AR model coefficient to be measured as an observation vector Xobs;
(2) establishing a model: taking the AR model coefficient of the fault-free sample as a historical observation vector of the MSET model, constructing a historical memory matrix, and establishing the MSET model;
(3) and (3) real-time evaluation: and inputting the AR model coefficient of the sample to be tested into the MSET model as an observation vector Xobs to obtain a reconstructed AR model coefficient, namely an estimation vector Xest, respectively substituting the estimation vector Xest and the observation vector Xobs into the AR model of the sample signal to be tested, and obtaining respective residual sequences through time sequence modeling, so as to obtain the root mean square value Difference (DR) of the two residual sequences of the performance degradation index, and drawing a performance degradation curve of the rolling bearing.
2. The method for evaluating the degradation of the performance of an AR-MSET-based rolling bearing according to claim 1, wherein the specific content of the extracted features is:
(a) establishing an AR model by using the first 100 groups of non-fault samples and the 982 groups of samples to be tested in the whole life cycle;
(b) and extracting autoregressive coefficients and residual errors of the AR model, determining the order of the AR model to be 30 according to a BIC (building information center) criterion, taking the autoregressive coefficients of the first 100 groups of fault-free samples as historical observation vectors, and taking the autoregressive coefficients of 982 groups of samples to be measured in the full life cycle as the observation vectors input into the MSET model.
3. The method for evaluating the performance degradation of an AR-MSET-based rolling bearing according to claim 1, wherein the concrete contents of the established model are: and (3) using the autoregressive coefficients of the first 100 groups of fault-free samples as historical observation vectors to construct a historical memory matrix and establish an MEST model.
4. The method for evaluating the performance degradation of an AR-MSET-based rolling bearing according to claim 1, wherein the real-time evaluation specifically comprises: after the MSET model is established, auto-regression coefficients of 982 groups of samples to be measured in the full life cycle are taken as observation vectors and sequentially input into the MSET model to obtain observation vectors (namely reconstructed auto-regression coefficients), the observation vectors are substituted into the AR model of the original sample signal to be measured, a reconstructed residual sequence can be obtained through time sequence modeling, finally, the difference value of the RMS of the reconstructed residual sequence and the RMS of the original signal to be measured residual sequence is calculated, so that the DR index of the fault degree can be obtained, and a performance degradation curve is drawn.
5. Result verification of the rolling bearing performance degradation evaluation method based on the multivariate state estimation model according to claims 1 to 4, characterized by comprising the steps of:
(a) determining the performance degradation starting time of the rolling bearing by using a 3 sigma criterion in statistics, and when the DR value of continuous 3 samples to be measured exceeds an early warning threshold value T (te) at the time of te, determining that the performance of the rolling bearing is changed;
(b) the kurtosis is used as a fault degree index of a bearing full-life fatigue test, comparative analysis is carried out, and the superiority of the bearing full-life fatigue test is verified;
(c) verifying the reliability of the obtained performance degradation curve by using bearing accelerated fatigue test data;
(d) and verifying the correctness of the evaluation result after analyzing the sample signal to be tested by using an envelope spectrum analysis method based on adaptive frequency band filtering and envelope demodulation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010516225.8A CN111504647A (en) | 2020-06-09 | 2020-06-09 | AR-MSET-based performance degradation evaluation method for rolling bearing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010516225.8A CN111504647A (en) | 2020-06-09 | 2020-06-09 | AR-MSET-based performance degradation evaluation method for rolling bearing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111504647A true CN111504647A (en) | 2020-08-07 |
Family
ID=71877241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010516225.8A Pending CN111504647A (en) | 2020-06-09 | 2020-06-09 | AR-MSET-based performance degradation evaluation method for rolling bearing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111504647A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112036089A (en) * | 2020-09-03 | 2020-12-04 | 华能国际电力股份有限公司玉环电厂 | Coal mill fault early warning method based on DPC-MND and multivariate state estimation |
| CN112182912A (en) * | 2020-10-27 | 2021-01-05 | 南京航空航天大学 | Manufacturing equipment main shaft bearing health assessment method based on probability description and spectrum analysis |
| CN113237619A (en) * | 2021-04-16 | 2021-08-10 | 江苏方天电力技术有限公司 | Fault early warning method, device, equipment and storage medium for variable-speed rotating machinery vibration |
| CN113834657A (en) * | 2021-09-24 | 2021-12-24 | 北京航空航天大学 | Bearing fault early warning and diagnosis method based on improved MSET and frequency spectrum characteristics |
| CN116026420A (en) * | 2023-03-30 | 2023-04-28 | 昆山合力泰汽车检具有限公司 | Parameter detection method and system based on bearing machining |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880170A (en) * | 2012-10-08 | 2013-01-16 | 南京航空航天大学 | System failure early warning method based on baseline model and Bayesian factor |
| CN104729853A (en) * | 2015-04-10 | 2015-06-24 | 华东交通大学 | Rolling bearing performance degradation evaluation device and method |
| CN106053066A (en) * | 2016-05-23 | 2016-10-26 | 华东交通大学 | Antifriction bearing performance degradation assessment method based on empirical mode decomposition and logistic regression |
| CN106885697A (en) * | 2017-03-17 | 2017-06-23 | 华东交通大学 | The performance degradation assessment method of the rolling bearing based on FCM HMM |
| CN109298697A (en) * | 2018-11-13 | 2019-02-01 | 远光软件股份有限公司 | Thermal power plant's various parts working state evaluation method based on DBM Dynamic Baseline Model |
-
2020
- 2020-06-09 CN CN202010516225.8A patent/CN111504647A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880170A (en) * | 2012-10-08 | 2013-01-16 | 南京航空航天大学 | System failure early warning method based on baseline model and Bayesian factor |
| CN104729853A (en) * | 2015-04-10 | 2015-06-24 | 华东交通大学 | Rolling bearing performance degradation evaluation device and method |
| CN106053066A (en) * | 2016-05-23 | 2016-10-26 | 华东交通大学 | Antifriction bearing performance degradation assessment method based on empirical mode decomposition and logistic regression |
| CN106885697A (en) * | 2017-03-17 | 2017-06-23 | 华东交通大学 | The performance degradation assessment method of the rolling bearing based on FCM HMM |
| CN109298697A (en) * | 2018-11-13 | 2019-02-01 | 远光软件股份有限公司 | Thermal power plant's various parts working state evaluation method based on DBM Dynamic Baseline Model |
Non-Patent Citations (3)
| Title |
|---|
| 刘涛 等: "基于多元状态估计和偏离度的电厂风机故障预警", 《动力工程学报》 * |
| 张龙 等: "基于时序模型和自联想神经网络的齿轮故障程度评估", 《振动与冲击》 * |
| 韩万里 等: "基于PCA和多元状态估计的引风机故障预警", 《热能动力工程》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112036089A (en) * | 2020-09-03 | 2020-12-04 | 华能国际电力股份有限公司玉环电厂 | Coal mill fault early warning method based on DPC-MND and multivariate state estimation |
| CN112182912A (en) * | 2020-10-27 | 2021-01-05 | 南京航空航天大学 | Manufacturing equipment main shaft bearing health assessment method based on probability description and spectrum analysis |
| CN112182912B (en) * | 2020-10-27 | 2024-03-22 | 南京航空航天大学 | Manufacturing equipment spindle bearing health assessment method based on probability description and spectrum analysis |
| CN113237619A (en) * | 2021-04-16 | 2021-08-10 | 江苏方天电力技术有限公司 | Fault early warning method, device, equipment and storage medium for variable-speed rotating machinery vibration |
| CN113834657A (en) * | 2021-09-24 | 2021-12-24 | 北京航空航天大学 | Bearing fault early warning and diagnosis method based on improved MSET and frequency spectrum characteristics |
| CN116026420A (en) * | 2023-03-30 | 2023-04-28 | 昆山合力泰汽车检具有限公司 | Parameter detection method and system based on bearing machining |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111504647A (en) | AR-MSET-based performance degradation evaluation method for rolling bearing | |
| CN111353482B (en) | LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method | |
| CN110414155B (en) | Fan component temperature abnormity detection and alarm method with single measuring point | |
| CN104764869B (en) | Transformer gas fault diagnosis and alarm method based on multidimensional characteristics | |
| CN113569338B (en) | Gas compressor rotating stall early warning method based on time expansion convolutional network | |
| CN110414154B (en) | Fan component temperature abnormity detection and alarm method with double measuring points | |
| CN105275833A (en) | CEEMD (Complementary Empirical Mode Decomposition)-STFT (Short-Time Fourier Transform) time-frequency information entropy and multi-SVM (Support Vector Machine) based fault diagnosis method for centrifugal pump | |
| CN108760266A (en) | The virtual degeneration index building method of mechanical key component based on learning distance metric | |
| CN112183344B (en) | Large unit friction fault analysis method and system based on waveform and dimensionless learning | |
| CN114167838B (en) | Multi-scale health assessment and fault prediction method for servo system | |
| CN105930629B (en) | A kind of on-line fault diagnosis method based on magnanimity service data | |
| CN113562562A (en) | Elevator safety early warning monitoring system and judgment method thereof | |
| CN108168924B (en) | Reciprocating compressor service life prediction method based on VMD (model-based decomposition) and MFSS (model-based decomposition) models | |
| CN111964909A (en) | Rolling bearing operation state detection method, fault diagnosis method and system | |
| CN109615126A (en) | A kind of bearing residual life prediction technique | |
| CN113947017A (en) | Method for predicting residual service life of rolling bearing | |
| CN117074961A (en) | Variation self-encoder power battery abnormality detection method, system, device and storage medium | |
| CN105910806A (en) | Filling pump early health status monitoring method | |
| CN113742932A (en) | Method for predicting and diagnosing faults of gearbox of wind turbine generator | |
| CN114664063A (en) | Equipment grading alarm method based on general index trend analysis | |
| CN115496108A (en) | Fault monitoring method and system based on manifold learning and big data analysis | |
| CN110108474B (en) | Online monitoring and evaluating method and system for operation stability of rotary machine | |
| CN117454283A (en) | State evaluation method for wind turbine generator operation detection data | |
| CN114705432A (en) | Method and system for evaluating health state of explosion-proof motor bearing | |
| CN116910677A (en) | Industrial instrument fault diagnosis method and system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200807 |