CN111191740B - Fault diagnosis method for rolling bearing - Google Patents
Fault diagnosis method for rolling bearing Download PDFInfo
- Publication number
- CN111191740B CN111191740B CN202010024877.XA CN202010024877A CN111191740B CN 111191740 B CN111191740 B CN 111191740B CN 202010024877 A CN202010024877 A CN 202010024877A CN 111191740 B CN111191740 B CN 111191740B
- Authority
- CN
- China
- Prior art keywords
- fault
- rolling bearing
- dimensional
- pso
- scale
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention relates to a fault diagnosis method for a rolling bearing, which comprises the following steps: collecting different fault state signals of the rolling bearing; utilizing a generalized composite multi-scale weighted permutation entropy algorithm GCMWPE to extract fault features, and comprehensively constructing a high-dimensional fault feature set of the rolling bearing from multiple scales; carrying out dimensionality reduction on the high-dimensional fault feature by utilizing a supervised isocratic mapping manifold learning algorithm S-Isomap to obtain a low-dimensional fault feature set of the high-dimensional fault feature; and training the PSO-SVM by using a low-dimensional fault feature set, and diagnosing faults by using the trained PSO-SVM. The method solves the problem that the fault characteristics of the rolling bearing are difficult to extract, and can effectively and accurately diagnose each fault type of the rolling bearing.
Description
Technical Field
The invention relates to the technical field of rolling bearing fault analysis, in particular to a rolling bearing fault diagnosis method.
Background
The rolling bearing is widely applied as a part of a rotary machine which is easy to damage, and has important theoretical and practical significance for fault diagnosis.
The vibration signal of the rolling bearing is generally characterized by characteristics of non-smoothness and non-linearity, and therefore, a plurality of methods for measuring the non-linear time series complexity of a mechanical dynamic system are sequentially proposed and applied to the field of fault diagnosis. Among them, the multi-scale weighted permutation entropy (MWPE) integrates the advantages of the multi-scale entropy and the weighted permutation entropy, and can measure the complexity of the time series from multiple scales, and therefore, is widely applied to multiple fields. However, when the MWPE is applied to the rolling bearing feature extraction process, the following 3-point defects still exist: (1) the entropy estimation deviation of MWPE can increase along with the increase of the coarse-grained scale factor; (2) the MWPE coarse graining process ignores useful information on other coarse graining sequences and influences entropy value accuracy. (3) When the MWPE is subjected to coarse graining structure, the dynamic mutation behavior of an original signal can be neutralized to a certain extent by utilizing a mean value processing mode, and the characteristic extraction result is influenced. The key point of the fault diagnosis of the rolling bearing is feature extraction, however, the extracted fault features often have information redundancy and are not beneficial to subsequent processing.
Disclosure of Invention
In view of this, the present invention provides a method for diagnosing a fault of a rolling bearing, which solves the problem of difficulty in extracting a fault feature of the rolling bearing and can effectively and accurately diagnose each fault type of the rolling bearing.
The invention is realized by adopting the following scheme: a rolling bearing fault diagnosis method comprises the following steps:
collecting different fault state signals of the rolling bearing;
utilizing a generalized composite multi-scale weighted permutation entropy algorithm (GCMWPE) to extract fault features, and comprehensively constructing a rolling bearing high-dimensional fault feature set from multiple scales;
carrying out dimensionality reduction on the high-dimensional fault feature by utilizing a supervision isocratic mapping manifold learning algorithm (S-Isomap) to obtain a low-dimensional fault feature set of the high-dimensional fault feature;
and training a particle swarm optimization support vector machine (PSO-SVM) by using a low-dimensional fault feature set, and diagnosing faults by using the trained particle swarm optimization support vector machine (PSO-SVM).
Further, the acquiring of different fault state signals of the rolling bearing specifically includes: and acquiring radial vibration acceleration signals of the rolling bearing in a normal state, an outer ring fault state, an inner ring fault state and a rolling body fault state by using an acceleration sensor.
Further, the fault feature extraction is performed by using a generalized composite multi-scale weighted permutation entropy algorithm (GCMWPE), and the method for comprehensively constructing the high-dimensional fault feature set of the rolling bearing from multiple scales specifically comprises the following steps: and carrying out entropy characteristic extraction on each group of vibration signals by utilizing a generalized composite multi-scale weighted arrangement entropy algorithm (GCMWPE) to construct an original high-dimensional characteristic set.
Specifically, the extracting the features of the entropy value of each group of vibration signals by using a generalized composite multi-scale weighted arrangement entropy algorithm (GCMWPE) to construct an original high-dimensional feature set specifically includes the following steps:
step S11: time series X ═ X for different fault status signals 1 ,x 2 ,...,x N The generalized composite coarse graining sequence is calculated by adopting the following formula
In the formula (I), the compound is shown in the specification,
representing a kth generalized composite coarse-grained sequence under the scale s, wherein s is a scale factor, tau is time delay, and N is the length of a time sequence;
step S12: for each scale factor s, calculating each generalized coarse grained sequence
A WPE value of (a);
step S13: homogenizing a plurality of WPE values under the same scale to obtain a GCMWPE value of a corresponding fault signal under the scale of s, wherein the corresponding expression is as follows:
further, the GCMWPE parameters are set as follows: the length of the time sequence is set to be N4096, the scale factor s is set to be 20, the time delay tau is set to be 1, and the embedding dimension m is set to be 6.
Further, the training of the particle swarm optimization support vector machine (PSO-SVM) by using the low-dimensional fault feature set and the fault diagnosis by using the trained particle swarm optimization support vector machine (PSO-SVM) specifically include the following steps:
step S21: randomly dividing each fault in the low-dimensional fault feature set into a training set and a test sample set according to the proportion of 1: 4; respectively carrying out normalization processing on the test sample set and the training set;
step S22: defining a kernel function in the SVM model as a radial basis function, and performing parameter optimization selection by using a Particle Swarm Optimization (PSO) algorithm;
step S23: and (4) using the training set to train a PSO-SVM model, and then carrying out diagnosis and identification on the test sample set samples by using the trained PSO-SVM model.
Further, in step S2, defining the average correct recognition rate of the training sample after 3-fold intersection as an fitness value, setting the particle swarm size as 10, the termination iteration as 100, the local search capability as 2, and the global search capability as 2, so as to obtain the optimal penalty factor and kernel function parameter of the PSO-SVM model.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention provides a new GCMWPE algorithm aiming at the defects of MWPE coarse graining, and the algorithm is utilized to comprehensively extract the fault characteristic information of the rolling bearing.
2. The invention introduces an S-Isomap algorithm to carry out secondary feature extraction on the high-dimensional fault feature set, obtains the low-dimensional fault feature set which is easy to distinguish fault types, and improves the fault diagnosis performance.
3. The invention introduces a PSO-SVM classifier to diagnose the GCMWPE + S-Isomap feature set and effectively identify the fault type of the rolling bearing.
Drawings
FIG. 1 is a schematic flow chart of a method according to an embodiment of the present invention.
Fig. 2 is a time domain waveform diagram of the rolling bearing according to the embodiment of the invention in different states.
Fig. 3 is a flowchart of the GCMWPE algorithm according to the embodiment of the present invention.
Fig. 4 shows the GCMWPE feature extraction result according to the embodiment of the present invention.
FIG. 5 shows the S-Isomap dimension reduction result of the GCMWPE feature set according to the embodiment of the present invention.
Fig. 6 is a result of feature set recognition after dimension reduction by the PSO-SVM according to the embodiment of the present invention.
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
As shown in fig. 1, the embodiment provides a rolling bearing fault diagnosis method, which uses rolling bearing signal data collected by a power transmission system fault diagnosis experiment table developed by Spectra Quest company as an example for performing method verification. The rotation speed of the input shaft is 20Hz, the load current is 0A, the sampling frequency is 3000HZ, and 4096 sampling points are set. The method comprises the following steps:
collecting different fault state signals of the rolling bearing;
utilizing a generalized composite multi-scale weighted permutation entropy algorithm (GCMWPE) to extract fault features, and comprehensively constructing a rolling bearing high-dimensional fault feature set from multiple scales;
carrying out dimensionality reduction on the high-dimensional fault feature by utilizing a supervision isocratic mapping manifold learning algorithm (S-Isomap) to obtain a low-dimensional fault feature set of the high-dimensional fault feature;
and training a particle swarm optimization support vector machine (PSO-SVM) by using a low-dimensional fault feature set, and diagnosing faults by using the trained PSO-SVM.
In this embodiment, the acquiring different fault state signals of the rolling bearing specifically includes: and acquiring radial vibration acceleration signals of the rolling bearing in a normal state, an outer ring fault state, an inner ring fault state and a rolling body fault state by using an acceleration sensor. In the embodiment, the acceleration sensor is used for respectively acquiring 100 groups of 4-state vibration acceleration signals under Normal (NOR) rolling bearing, Outer Ring Fault (ORF), Inner Ring Fault (IRF) and rolling element fault (BF), and the 4 states total 400 groups of sample signals, and the corresponding time domain waveforms are shown in fig. 2.
In this embodiment, the extracting of the fault feature is performed by using a generalized composite multi-scale weighted arrangement entropy algorithm (GCMWPE), and the fully constructing a high-dimensional fault feature set of the rolling bearing from multiple scales specifically includes: extracting entropy characteristics of each group of vibration signals by using a generalized composite multi-scale weighted arrangement entropy algorithm (GCMWPE) to construct an original high-dimensional characteristic set, wherein a flow chart of the algorithm of the GCMWPE is shown in figure 3, and entropy mean curves of different states of the rolling bearing are shown in figure 4.
The principle of the GCMWPE is as follows:
the Weighted Permutation Entropy (WPE) overcomes the defect that the Permutation Entropy (PE) only considers the sequence structure characteristics of sequences and ignores the amplitude characteristics, and the specific process is as follows:
(1) for time series X ═ X 1 ,x 2 ,...,x N Performing phase space reconstruction to obtain a series of subsequences
Where τ is the time delay and m is the embedding dimension.
(2) Calculating the weight value w of each subsequence i ：
(3) Random subsequence
Is represented by a weight value w i And arrangement mode pi i And (4) performing representation. For this time sequence X there are Q permutation patterns in common, the Q permutation pattern pi q The weighted probability value of (a) is:
(4) calculating a weighted permutation entropy WPE value of the time series X:
the multi-scale weighted permutation entropy (MWPE) overcomes the defect of WPE single-scale analysis, and can comprehensively represent time sequence complexity from multiple scales, and the specific process is as follows:
(1) carrying out coarse graining treatment on the time sequence X to obtain a coarse grain sequence y (s) ＝{y (s) (j)}：
Wherein s is a scale factor.
(2) Calculating the WPE values of the coarse grained sequences y(s) under different scale factors:
MWPE(X,m,τ,s)＝WPE(y (s) ,m,τ)；
in the formula, WPE (-) is a weighted permutation entropy algorithm.
The generalized composite multi-scale weighted permutation entropy algorithm process proposed by the embodiment is as follows:
(1) time series X for different fault status signals 1 ,x 2 ,...,x N The generalized composite coarse graining sequence is calculated by adopting the following formula
In the formula (I), the compound is shown in the specification,
represents the kth generalized composite coarse grained sequence at the scale s.
(2) For each scale factor s, calculating each generalized coarse grained sequence
WPE value of (a).
(3) And homogenizing a plurality of WPE values under the same scale to obtain a GCMWPE value of the corresponding fault signal under the scale s, wherein the corresponding expression is as follows:
in this embodiment, the GCMWPE parameters are set as follows: the length of the time sequence is set to be N4096, the scale factor s is set to be 20, the time delay tau is set to be 1, and the embedding dimension m is set to be 6. From FIG. 4, it can be seen that: (1) for the initial scale, the entropy value of the normal state of the rolling bearing obtained by GCMWPE is the largest in four states. For the actual working condition, when the rolling bearing is in a normal state, the vibration signal fluctuation is random, the randomness of the signal is high, the self-similarity is low, and the entropy value is large; when the bearing has a local fault, the vibration signal fluctuation has certain regularity, the regularity and the self-similarity of the signal are higher, and the entropy value is smaller, so that the GCMWPE algorithm is suitable for judging whether the rolling bearing fault occurs or not. (2) The GCMWPE method provided by the invention has the advantages that the entropy mean curve is smooth, four types of samples can be effectively distinguished, and the effectiveness of comprehensively extracting the fault features of the rolling bearing by using the algorithm is verified.
Preferably, the fault feature set extracted by the GCMWPE algorithm has the characteristics of high dimension, nonlinearity, redundancy and the like, and the PSO-SVM classifier is directly used for fault recognition, so that the recognition time is increased and even the recognition effect is influenced. Therefore, in the embodiment, the supervised isocratic mapping (S-Isomap) algorithm is adopted to perform the dimension reduction processing on the fault type, a low-dimensional feature set which is easy to distinguish the fault type is extracted, and the dimension reduction result is shown in fig. 5. Wherein the parameters of the S-Isomap algorithm are set as follows: the intrinsic dimension is 3, the neighbor parameter is 70, and the parameter beta is the average value of Euclidean distances of all sample points; the parameter α is 0.4. In the dimension reduction result of the GCMWPE feature set by the S-Isomap, four types of samples can be effectively and completely distinguished, and the four types of samples have good aggregative property, which shows that the feature extraction mode of combining the GCMWPE and the S-Isomap provided by the embodiment can effectively extract a low-dimensional and sensitive feature set which is easy to distinguish rolling bearing fault feature information.
Wherein the principle of the supervised isocratic mapping (S-Isomap) manifold learning algorithm is as follows:
for an input sample set U ═ U 1 ,u 2 ,...,u N ] T Specifically, the S-Isomap process is as follows:
(1) defining a neighborhood graph G containing all samples, and constructing a supervised distance matrix D s ＝{d s (u i ,u j )}. If the sample point u i Is u j K of (1) is adjacent to the point, then u i And u j Connected by edges with a side length d s (u i ,u j ) (ii) a Otherwise, no edge connection is performed:
in the formula, d (u) i ,u j ) Represents a sample point u i And u j The euclidean distance between;
represents u i The tag information of (a); beta is used for inhibiting the excessive rapid increase of the inter-class distance and is defined as the average value of Euclidean distances of all sample points; alpha is used for adjusting the similarity between different label sample points.
(2) And calculating the shortest path by utilizing a Dijkstra method, and defining the shortest path between any two points on the graph G as the geodesic distance between the two points.
(3) And performing low-dimensional mapping on the geodesic distance matrix by using a multidimensional scaling analysis (MDS) algorithm to obtain a low-dimensional embedding result Y.
In this embodiment, the training of the particle swarm optimization support vector machine (PSO-SVM) by using the low-dimensional fault feature set and the fault diagnosis by using the trained particle swarm optimization support vector machine (PSO-SVM) specifically include the following steps:
step S21: randomly dividing each fault in the low-dimensional fault feature set into a training set and a test sample set according to the proportion of 1: 4; respectively carrying out normalization processing on the test sample set and the training set;
step S22: defining a kernel function in the SVM model as a radial basis function, and performing parameter optimization selection by using a PSO algorithm;
step S23: and using the training set for training (PSO-SVM) models, and then carrying out diagnosis and identification on the test sample set samples by using the trained (PSO-SVM) models.
In this embodiment, in step S2, the average correct recognition rate after 3-fold intersection of the training samples is defined as an fitness value, the particle swarm size is set to 10, the termination iteration is set to 100, the local search capability is set to 2, and the global search capability is set to 2, so as to obtain the optimal penalty factor and kernel function parameter of the PSO-SVM model.
The recognition result of the sample of the test sample set in this embodiment is shown in fig. 6. As shown in fig. 6, the fault diagnosis method provided in this embodiment can effectively identify each fault type, and the identification rate reaches 100%.
The foregoing is directed to preferred embodiments of the present invention, other and further embodiments of the invention may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow. However, any simple modification, equivalent change and modification of the above embodiments according to the technical essence of the present invention are within the protection scope of the technical solution of the present invention.
Claims (5)
1. A fault diagnosis method for a rolling bearing is characterized by comprising the following steps:
collecting different fault state signals of the rolling bearing;
utilizing a generalized composite multi-scale weighted permutation entropy algorithm GCMWPE to extract fault features, and comprehensively constructing a high-dimensional fault feature set of the rolling bearing from multiple scales;
carrying out dimensionality reduction on the high-dimensional fault feature by utilizing a supervised isocratic mapping manifold learning algorithm S-Isomap to obtain a low-dimensional fault feature set of the high-dimensional fault feature;
training the PSO-SVM by using a low-dimensional fault feature set, and diagnosing faults by using the trained PSO-SVM;
the method comprises the following steps of extracting fault characteristics by utilizing a generalized composite multi-scale weighted permutation entropy algorithm GCMWPE, and comprehensively constructing a high-dimensional fault characteristic set of the rolling bearing from multiple scales: carrying out entropy characteristic extraction on each group of vibration signals by utilizing a generalized composite multi-scale weighted arrangement entropy algorithm GCMWPE (generalized composite multi-scale weighted arrangement entropy algorithm), and constructing an original high-dimensional characteristic set;
the method for extracting the entropy characteristics of each group of vibration signals by using the generalized composite multi-scale weighted permutation entropy algorithm GCMWPE to construct the original high-dimensional characteristic set specifically comprises the following steps:
step S11: time series X ═ X for different fault status signals 1 ,x 2 ,...,x N The generalized composite coarse graining sequence is calculated by adopting the following formula
In the formula (I), the compound is shown in the specification,
representing a kth generalized composite coarse-grained sequence under the scale s, wherein s is a scale factor, tau is time delay, and N is the length of a time sequence;
step S12: for each scale factor s, calculating each generalized composite coarse graining sequence respectively
A WPE value of (a);
step S13: homogenizing a plurality of WPE values under the same scale to obtain a GCMWPE value of a corresponding fault signal under the scale of s, wherein the corresponding expression is as follows:
2. The method for diagnosing the fault of the rolling bearing according to claim 1, wherein the collecting of the different fault state signals of the rolling bearing specifically comprises: and acquiring radial vibration acceleration signals of the rolling bearing in a normal state, an outer ring fault state, an inner ring fault state and a rolling body fault state by using an acceleration sensor.
3. The rolling bearing fault diagnosis method according to claim 1, wherein the GCMWPE parameters are set as follows: setting the time sequence length N as the number of sampling points, the scale factor s as 20, the time delay tau as 1 and the embedding dimension m as 6.
4. The rolling bearing fault diagnosis method according to claim 1, wherein the training of the particle swarm optimization support vector machine PSO-SVM by using the low-dimensional fault feature set specifically comprises the following steps:
step S21: randomly dividing each fault in the low-dimensional fault feature set into a training set and a test sample set according to the proportion of 1: 4; respectively carrying out normalization processing on the training set and the test sample set;
step S22: defining a kernel function in the SVM model as a radial basis function, and performing parameter optimization selection by using a Particle Swarm Optimization (PSO) algorithm;
step S23: and (4) using the training set to train a PSO-SVM model, and then carrying out diagnosis and identification on the test sample set samples by using the trained PSO-SVM model.
5. The rolling bearing fault diagnosis method according to claim 4, wherein in step S2, the average correct recognition rate of the training samples after 3 folds is defined as a fitness value, the particle swarm size is set to be 10, the termination iteration is set to be 100, the local search capability is set to be 2, and the global search capability is set to be 2, so as to obtain the optimal penalty factor and kernel function parameter of the PSO-SVM model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010024877.XA CN111191740B (en) | 2020-01-10 | 2020-01-10 | Fault diagnosis method for rolling bearing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010024877.XA CN111191740B (en) | 2020-01-10 | 2020-01-10 | Fault diagnosis method for rolling bearing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111191740A CN111191740A (en) | 2020-05-22 |
| CN111191740B true CN111191740B (en) | 2022-08-05 |
Family
ID=70708599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010024877.XA Active CN111191740B (en) | 2020-01-10 | 2020-01-10 | Fault diagnosis method for rolling bearing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111191740B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738309B (en) * | 2020-06-03 | 2024-07-12 | 哈尔滨工业大学 | Multi-scale analysis and integrated learning gas sensor fault mode identification method |
| CN112033463B (en) * | 2020-09-02 | 2022-09-06 | 哈尔滨工程大学 | Nuclear power equipment state evaluation and prediction integrated method and system |
| CN112257530B (en) * | 2020-10-13 | 2023-10-20 | 西安电子科技大学 | Rolling bearing fault diagnosis method based on blind signal separation and support vector machine |
| CN112577743B (en) * | 2020-11-06 | 2021-08-17 | 中国矿业大学 | Rolling bearing fault diagnosis method based on maximum local boundary criterion |
| CN112761843A (en) * | 2021-02-18 | 2021-05-07 | 哈尔滨工程大学 | Common rail oil injector fault diagnosis method |
| CN114139293A (en) * | 2021-08-18 | 2022-03-04 | 福州大学 | Rolling bearing fault diagnosis method and system |
| CN114398927A (en) * | 2022-01-14 | 2022-04-26 | 中国人民解放军92728部队 | Vibration signal identification method and system based on improved multi-scale permutation entropy |
| CN117314883B (en) * | 2023-10-27 | 2024-04-16 | 国网四川省电力公司电力科学研究院 | Power distribution network fault line selection method and system based on EWT and VGGNet |
| CN117874436B (en) * | 2024-03-12 | 2024-07-02 | 烟台哈尔滨工程大学研究院 | Composite multi-scale bidirectional multi-entropy-based marine fuel system diagnosis method and medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104849050A (en) * | 2015-06-02 | 2015-08-19 | 安徽工业大学 | Rolling bearing fault diagnosis method based on composite multi-scale permutation entropies |
| CN106500991A (en) * | 2016-10-14 | 2017-03-15 | 石家庄铁道大学 | Based on the bearing fault signal characteristic extracting methods that self-adapting multi-dimension AVGH is converted |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107941537B (en) * | 2017-10-25 | 2019-08-27 | 南京航空航天大学 | A kind of mechanical equipment health state evaluation method |
-
2020
- 2020-01-10 CN CN202010024877.XA patent/CN111191740B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104849050A (en) * | 2015-06-02 | 2015-08-19 | 安徽工业大学 | Rolling bearing fault diagnosis method based on composite multi-scale permutation entropies |
| CN106500991A (en) * | 2016-10-14 | 2017-03-15 | 石家庄铁道大学 | Based on the bearing fault signal characteristic extracting methods that self-adapting multi-dimension AVGH is converted |
Non-Patent Citations (2)
| Title |
|---|
| Weighted multiscale permutation entropy of financial time series;Yin Yi 等;《NONLINEAR DYNAMICS》;20141217;第78卷(第4期);全文 * |
| 振动机械滚动轴承故障诊断研究;杨继林;《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》;20190215;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111191740A (en) | 2020-05-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111191740B (en) | Fault diagnosis method for rolling bearing | |
| CN111103139A (en) | Rolling bearing fault diagnosis method based on GRCMSE and manifold learning | |
| CN112036301B (en) | Driving motor fault diagnosis model construction method based on intra-class feature transfer learning and multi-source information fusion | |
| Wang et al. | A novel weighted sparse representation classification strategy based on dictionary learning for rotating machinery | |
| Sinitsin et al. | Intelligent bearing fault diagnosis method combining mixed input and hybrid CNN-MLP model | |
| CN109916628A (en) | Based on the Fault Diagnosis of Roller Bearings for improving multiple dimensioned amplitude perception arrangement entropy | |
| CN105910827B (en) | Induction machine method for diagnosing faults based on identification convolution feature learning | |
| CN105760839A (en) | Bearing fault diagnosis method based on multi-feature manifold learning and support vector machine | |
| CN110110768B (en) | Rolling bearing fault diagnosis method based on parallel feature learning and multiple classifiers | |
| CN112257530B (en) | Rolling bearing fault diagnosis method based on blind signal separation and support vector machine | |
| Wu et al. | A transformer-based approach for novel fault detection and fault classification/diagnosis in manufacturing: A rotary system application | |
| CN112577743B (en) | Rolling bearing fault diagnosis method based on maximum local boundary criterion | |
| CN110084316B (en) | Fault diagnosis method based on fine time-shifting multi-scale arrangement entropy and firefly algorithm optimization support vector machine | |
| CN112819059A (en) | Rolling bearing fault diagnosis method based on popular retention transfer learning | |
| Yang et al. | Enhanced hierarchical symbolic dynamic entropy and maximum mean and covariance discrepancy-based transfer joint matching with Welsh loss for intelligent cross-domain bearing health monitoring | |
| CN111898644B (en) | Intelligent identification method for health state of aerospace liquid engine under fault-free sample | |
| Zhang et al. | A bearing fault diagnosis method based on multiscale dispersion entropy and GG clustering | |
| CN110991422A (en) | Rolling bearing fault diagnosis method based on multi-element time-shifting multi-scale permutation entropy | |
| CN114638251A (en) | Rolling bearing fault diagnosis method based on RCMRDE and JMIM feature selection | |
| AU2021102131A4 (en) | Fault diagnosis method of rolling bearing based on generalized composite multi-scale weighted permutation entropy and supervised isometric mapping | |
| CN109726770A (en) | A kind of analog circuit fault testing and diagnosing method | |
| CN114118174A (en) | Rolling bearing fault diagnosis method and system | |
| CN115273791A (en) | Industrial equipment fault detection method and device based on acoustic feature driving | |
| CN113790890B (en) | Wavelet packet decomposition weight fuzzy entropy and ELM-based bearing fault classification method and device | |
| CN114117923A (en) | High-voltage parallel reactor state judgment system and method based on chaotic feature space |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230327 Address after: 214200 China Yixing Environmental Science Park, Yixing City, Wuxi City, Jiangsu Province Patentee after: B-TOHIN MACHINE (JIANGSU) Co.,Ltd. Address before: Fuzhou University, No.2, wulongjiang North Avenue, Fuzhou University Town, Minhou County, Fuzhou City, Fujian Province Patentee before: FUZHOU University |