CN109612729A - A kind of malfunction recognition methods of port Machine Trolley Wheel Bearings - Google Patents
A kind of malfunction recognition methods of port Machine Trolley Wheel Bearings Download PDFInfo
- Publication number
- CN109612729A CN109612729A CN201811595105.0A CN201811595105A CN109612729A CN 109612729 A CN109612729 A CN 109612729A CN 201811595105 A CN201811595105 A CN 201811595105A CN 109612729 A CN109612729 A CN 109612729A
- Authority
- CN
- China
- Prior art keywords
- time
- matrix
- sample
- frequency
- wheel bearings
- 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 20
- 230000007257 malfunction Effects 0.000 title claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims abstract description 24
- 238000013480 data collection Methods 0.000 claims abstract description 15
- 230000009467 reduction Effects 0.000 claims abstract description 14
- 238000013145 classification model Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 238000010219 correlation analysis Methods 0.000 claims abstract description 5
- 239000000284 extract Substances 0.000 claims abstract description 5
- 238000005192 partition Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims abstract description 4
- 238000001228 spectrum Methods 0.000 claims description 19
- 238000009826 distribution Methods 0.000 claims description 12
- 230000001133 acceleration Effects 0.000 claims description 7
- 230000004069 differentiation Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 2
- 238000007796 conventional method Methods 0.000 abstract description 2
- 230000007812 deficiency Effects 0.000 abstract description 2
- 238000013135 deep learning Methods 0.000 description 5
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 4
- 238000012631 diagnostic technique Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 229910052742 iron Inorganic materials 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000003585 interneuronal effect Effects 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
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
Landscapes
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The present invention discloses the malfunction recognition methods of port Machine Trolley Wheel Bearings, is that port Machine Trolley Wheel Bearings vibration signal data even partition forms multiple samples under the different faults state by acquisition, building forms tag along sort matrix；All samples are carried out with time domain, frequency domain and time and frequency domain characteristics to extract to obtain characteristic respectively, establishes the higher-dimension initial characteristic data collection matrix using total sample number as line number, using characteristic as columns；Method is combined using Pearson correlation coefficient and residual analysis, correlation analysis is carried out to obtained characteristic parameter, extracts and differentiates that feature to higher-dimension initial characteristic data collection matrix dimensionality reduction, obtains sample characteristics matrix；By sample characteristics matrix after dimensionality reduction and corresponding label matrix, depth confidence network algorithm classification based training is imported, bearing fault state classification model is obtained.The present invention can accurately and effectively detect bearing fault, overcome deficiency of the conventional method in bearing fault identification.
Description
Technical field
The present invention relates to change system malfunction monitoring diagnostic techniques field, more particularly to one kind based on related coefficient and
The malfunction recognition methods of the port Machine Trolley Wheel Bearings of deep learning.
Background technique
Port board bearing is that a kind of bearing capacity is big, working speed is low and the frequent rolling bearing of work, is held in operation
By compared with big load.Bearing, which once breaks down, can seriously affect production, at the same bearing repair accordingly replacement the duty cycle it is longer,
This will lead to larger economic loss.It is therefore desirable to the production work efficiency with raising is monitored to bearing fault state.It passes
The bearing fault detection technology of system mainly includes iron spectrum diagnostic techniques and temperature diagnostic technology etc., but iron paving diagnostic techniques is only fitted
For the bearing failure diagnosis of oil lubrication, do not have generalization；Temperature diagnostic technology is preferable to bearing burn judgement, but only
Simple and regular suitable for machine middle (center) bearing diagnoses.
Summary of the invention
In view of the technical drawbacks of the prior art, it is an object of the present invention to provide a kind of events of port Machine Trolley Wheel Bearings
Hinder state identification method.
The technical solution adopted to achieve the purpose of the present invention is:
A kind of malfunction recognition methods of port Machine Trolley Wheel Bearings, comprising the following steps:
S1, vibrating sensor is installed on the Machine Trolley Wheel Bearings of port, is acquired by vibrating sensor and is transported under different faults classification
Turn the bear vibration acceleration signal of state；
S2, the bearing vibration signal data even partition under different faults state is formed to multiple samples, every kind of bearing event
Barrier state has the sample set formed by N number of sample, and total sample number T=N*C, C are bearing fault classification numbers；By bearing fault class
It is other that corresponding sample is marked, mark value 1,2 ... C, building form tag along sort matrix L=T × 1, wherein line number with
Total sample number is mutually all T, and columns is 1 column；
S3, it all samples is carried out with time domain, frequency domain and time and frequency domain characteristics respectively extracts to obtain characteristic B, then with sample
Line number of this sum T as higher-dimension initial characteristic data collection is obtained using characteristic B as the columns of higher-dimension initial characteristic data collection
To higher-dimension initial characteristic data collection matrix T × B；
S4, method is combined using Pearson correlation coefficient and residual analysis, to obtained higher-dimension initial characteristic data
Collect matrix T × B and carry out correlation analysis, extracts Z feature of most predetermined differentiation degree to higher-dimension initial characteristic data collection square
Battle array dimensionality reduction, obtaining sample characteristics matrix is T × Z；
S5, in a computer sample characteristics matrix T × Z after input dimensionality reduction and corresponding tag along sort matrix L, import
Depth confidence network algorithm carries out classification based training, obtains bearing fault state classification model；
S6, the port Machine Trolley Wheel Bearings vibration using the bearing fault state classification model, by step S3, S4 to acquisition
Acceleration signal carries out feature extraction and Feature Dimension Reduction, and using the eigenmatrix after dimensionality reduction as mode input, output state is known
Other result.
The vibrating sensor is piezoelectric vibration pickup.
The temporal signatures include mean value, root-mean-square value, peak value, variance, peak-to-peak value, signal energy, crest factor, high and steep
Degree, pulse index, the degree of bias and nargin coefficient；
The frequency domain character includes that power spectrum and power spectrum mean value, power spectrum variance, the power spectrum degree of bias, power spectrum are high and steep
Degree and spectrum peak；
The time and frequency domain characteristics include that distribution variance, time-frequency energy be at any time at any time for time-frequency gross energy, time-frequency energy
It is distributed that the degree of bias, that time-frequency energy is distributed kurtosis, time-frequency energy at any time is inclined with frequency distribution with frequency distribution variance, time-frequency energy
Degree, time-frequency energy are with frequency distribution kurtosis.
The malfunction recognition methods of port Machine Trolley Wheel Bearings proposed by the present invention based on related coefficient and deep learning,
It is theoretical using correlation analysis algorithm and deep learning, the effective information in bearing signal data is excavated profoundly, it can be quasi-
Bearing fault is effectively really detected, overcomes deficiency of the conventional method in bearing fault identification.
The malfunction recognition methods of port Machine Trolley Wheel Bearings proposed by the present invention based on related coefficient and deep learning,
By carrying out Pearson correlation coefficient and residual analysis dimension-reduction treatment to high dimensional feature data set, axis is obtained after carrying out classification processing
Hold malfunction disaggregated model, compared later with Bayes classifier, using test data to malfunction disaggregated model into
Row test, objective evaluation classification performance, as found from the results, the malfunction identification side based on related coefficient and deep learning
Method is more acurrate, improves the accuracy rate of bearing fault state, is of great significance to bearing fault identification, is improving production efficiency
Aspect is also of great significance.
Detailed description of the invention
Fig. 1 is the identification process figure of the malfunction recognition methods of port Machine Trolley Wheel Bearings of the invention；
Fig. 2 is the depth confidence network structure that the present invention uses.
Specific embodiment
The present invention is described in further detail below in conjunction with the drawings and specific embodiments.It should be appreciated that described herein
Specific embodiment be only used to explain the present invention, be not intended to limit the present invention.
As shown in Figs. 1-2, the malfunction recognition methods of port Machine Trolley Wheel Bearings of the invention, includes the following steps:
Step 1: installing vibrating sensor on the Machine Trolley Wheel Bearings of port, different faults classification is acquired by vibrating sensor
The bear vibration acceleration signal of lower operating；
As one embodiment of the present invention, the bearing fault status categories include that fault diameter is 0.007 English
Very little, 0.014 inch and 0.021 inch of three classification.
Wherein, the vibrating sensor is piezoelectric vibration pickup.
Step 2: (such as fault diameter is 0.007 inch, 0.014 inch and 0.021 English under acquisition different faults classification
Very little three kinds) bear vibration acceleration signal, then by the vibration signal data under each malfunction according to setting sampling week
Phase even partition forms multiple samples, then every kind of bearing fault state has the sample set formed by N number of sample, total sample number T
=N*C, C are bearing fault classification numbers, if bearing fault status categories have 3, C=3；Finally according to fault category to corresponding
Sample be marked, mark value 1,2 ... C, so that building forms tag along sort matrix L=T × 1, wherein line number and sample
Sum is mutually all T, and columns is 1 column；
It extracts to obtain characteristic B Step 3: carrying out all samples respectively time domain, frequency domain and time and frequency domain characteristics, then
Using total sample number T as the line number of higher-dimension initial characteristic data collection, using characteristic B as the column of higher-dimension initial characteristic data collection
Number, obtains higher-dimension initial characteristic data collection matrix T × B；
As one embodiment of the present invention, wherein temporal signatures include: mean value, root-mean-square value, peak value, variance, peak
Peak value, signal energy, crest factor, kurtosis, pulse index, the degree of bias and nargin coefficient.
Frequency domain character includes: power spectrum and power spectrum mean value, power spectrum variance, the power spectrum degree of bias, power spectrum kurtosis and function
Rate spectrum peak.
Time and frequency domain characteristics include: that distribution variance, time-frequency energy are distributed partially at any time at any time for time-frequency gross energy, time-frequency energy
Degree, time-frequency energy are distributed kurtosis, time-frequency energy with frequency distribution variance, time-frequency energy with the frequency distribution degree of bias, time-frequency at any time
Energy is with frequency distribution kurtosis.
Step 4: method is combined using Pearson correlation coefficient and residual analysis, to obtained higher-dimension primitive character
Data set matrix T × B carries out correlation analysis, by extracting the scheduled Z feature with corresponding differentiation degree (as extracted most
Have Z preferred feature of identification) to higher-dimension initial characteristic data collection matrix dimensionality reduction, the sample characteristics square after dimensionality reduction is obtained at this time
Battle array is T × Z；
As one embodiment of the present invention, wherein Pearson correlation coefficient indicates two correlations between variable X and Y
Degree, it may be assumed that
In formula, X is characterized parameter；Y is fault diameter；For the covariance of X and Y；For the covariance of X；For the covariance of Y,
Related coefficient between characteristic parameter and bearing wear amount is bigger, then correlation is stronger, otherwise correlation is weaker.
Residual analysis indicates the same characteristic ginseng value curves of different moments poor weighted mean therewith, algorithmic formula are as follows:
eIt is worth smaller, autocorrelation is stronger between characteristic parameter.
Step 5: inputting sample characteristics matrix and corresponding label matrix after dimensionality reduction in a computer, depth is imported
Confidence network algorithm carries out classification based training, obtains bearing fault state classification model.
Step 6: using the bearing fault state classification model, by Step 3: step 4 to the port locomotive wheel of acquisition
Bear vibration acceleration signal carries out feature extraction and Feature Dimension Reduction, defeated using the eigenmatrix after dimensionality reduction as mode input
Do well the result of identification.
As shown in Fig. 2, depth confidence neural network is by being restricted Boltzmann machine (RBM) network and the reversed biography of one layer of feedforward
Broadcast (BP) neural network composition.W is interneuronal connection weight in figure.
Wherein, for details, reference can be made to document " Hinton G.Deep Belief Nets [M] for depth confidence network theory
.Springer US,2011”。
The above is only a preferred embodiment of the present invention, it is noted that for the common skill of the art
For art personnel, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications
Also it should be regarded as protection scope of the present invention.
Claims (3)
1. a kind of malfunction recognition methods of port Machine Trolley Wheel Bearings, which comprises the following steps:
S1, vibrating sensor is installed on the Machine Trolley Wheel Bearings of port, is acquired by vibrating sensor and operates shape under different faults classification
The bear vibration acceleration signal of state；
S2, the bearing vibration signal data even partition under different faults state is formed into multiple samples, every kind of bearing fault shape
State has the sample set formed by N number of sample, and total sample number T=N*C, C are bearing fault classification numbers；By bearing fault classification pair
Corresponding sample is marked, mark value 1,2 ... C is constructed and is formed tag along sort matrix L=T × 1, wherein line number and sample
Sum is mutually all T, and columns is 1 column；
S3, it all samples is carried out with time domain, frequency domain and time and frequency domain characteristics respectively extracts to obtain characteristic B, it is then total with sample
Line number of the number T as higher-dimension initial characteristic data collection obtains height using characteristic B as the columns of higher-dimension initial characteristic data collection
Tie up initial characteristic data collection matrix T × B；
S4, method is combined using Pearson correlation coefficient and residual analysis, to obtained higher-dimension initial characteristic data collection square
Battle array T × B carries out correlation analysis, and higher-dimension initial characteristic data collection matrix drops in Z feature for extracting most predetermined differentiation degree
Dimension, obtaining sample characteristics matrix is T × Z；
S5, in a computer sample characteristics matrix T × Z after input dimensionality reduction and corresponding tag along sort matrix L, import depth
Confidence network algorithm carries out classification based training, obtains bearing fault state classification model；
S6, the port Machine Trolley Wheel Bearings vibration acceleration using the bearing fault state classification model, by step S3, S4 to acquisition
It spends signal and carries out feature extraction and Feature Dimension Reduction, the eigenmatrix after dimensionality reduction is identified as mode input, output state
As a result.
2. the malfunction recognition methods of port Machine Trolley Wheel Bearings as described in claim 1, which is characterized in that the vibrating sensing
Device is piezoelectric vibration pickup.
3. according to the malfunction recognition methods of port Machine Trolley Wheel Bearings described in claim steps 3, it is characterised in that: described
Temporal signatures include mean value, root-mean-square value, peak value, variance, peak-to-peak value, signal energy, crest factor, kurtosis, pulse index, partially
Degree and nargin coefficient；
The frequency domain character include power spectrum and power spectrum mean value, power spectrum variance, the power spectrum degree of bias, power spectrum kurtosis and
Spectrum peak；
The time and frequency domain characteristics include that distribution variance, time-frequency energy are distributed at any time at any time for time-frequency gross energy, time-frequency energy
The degree of bias, time-frequency energy be distributed at any time kurtosis, time-frequency energy with frequency distribution variance, time-frequency energy with the frequency distribution degree of bias, when
Frequency energy is with frequency distribution kurtosis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811595105.0A CN109612729A (en) | 2018-12-25 | 2018-12-25 | A kind of malfunction recognition methods of port Machine Trolley Wheel Bearings |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811595105.0A CN109612729A (en) | 2018-12-25 | 2018-12-25 | A kind of malfunction recognition methods of port Machine Trolley Wheel Bearings |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109612729A true CN109612729A (en) | 2019-04-12 |
Family
ID=66012447
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811595105.0A Pending CN109612729A (en) | 2018-12-25 | 2018-12-25 | A kind of malfunction recognition methods of port Machine Trolley Wheel Bearings |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109612729A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110146293A (en) * | 2019-06-04 | 2019-08-20 | 昆明理工大学 | A kind of Fault Diagnosis of Roller Bearings based on PCA and ELM |
| CN110490218A (en) * | 2019-06-10 | 2019-11-22 | 内蒙古工业大学 | A kind of rolling bearing fault self-learning method based on two-stage DBN |
| CN110646188A (en) * | 2019-10-14 | 2020-01-03 | 军事科学院系统工程研究院军用标准研究中心 | Fault diagnosis method for rotary mechanical equipment |
| CN110674892A (en) * | 2019-10-24 | 2020-01-10 | 北京航空航天大学 | Fault feature screening method based on weighted multi-feature fusion and SVM classification |
| CN110674991A (en) * | 2019-09-25 | 2020-01-10 | 国家能源集团谏壁发电厂 | OCSVM (online charging management system VM) -based method for detecting abnormality of primary fan of thermal power plant |
| CN111076933A (en) * | 2019-12-14 | 2020-04-28 | 西安交通大学 | Method for establishing sensitive characteristic index set and identifying health state of machine tool spindle bearing |
| CN111896254A (en) * | 2020-08-10 | 2020-11-06 | 山东大学 | Fault prediction system and method for variable-speed variable-load large rolling bearing |
| CN112320520A (en) * | 2020-11-09 | 2021-02-05 | 浙江新再灵科技股份有限公司 | Elevator abnormal vibration detection method based on residual error analysis |
| CN113255840A (en) * | 2021-06-30 | 2021-08-13 | 长江存储科技有限责任公司 | Fault detection and classification method, device, system and storage medium |
| CN113432886A (en) * | 2021-06-09 | 2021-09-24 | 中北大学 | Vehicle full-life cycle vibration impact testing method and device |
| CN114659785A (en) * | 2021-12-27 | 2022-06-24 | 三一重能股份有限公司 | Fault detection method and device for transmission chain of wind driven generator |
-
2018
- 2018-12-25 CN CN201811595105.0A patent/CN109612729A/en active Pending
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110146293A (en) * | 2019-06-04 | 2019-08-20 | 昆明理工大学 | A kind of Fault Diagnosis of Roller Bearings based on PCA and ELM |
| CN110490218A (en) * | 2019-06-10 | 2019-11-22 | 内蒙古工业大学 | A kind of rolling bearing fault self-learning method based on two-stage DBN |
| CN110490218B (en) * | 2019-06-10 | 2022-11-29 | 内蒙古工业大学 | Rolling bearing fault self-learning method based on two-stage DBN |
| CN110674991A (en) * | 2019-09-25 | 2020-01-10 | 国家能源集团谏壁发电厂 | OCSVM (online charging management system VM) -based method for detecting abnormality of primary fan of thermal power plant |
| CN110646188A (en) * | 2019-10-14 | 2020-01-03 | 军事科学院系统工程研究院军用标准研究中心 | Fault diagnosis method for rotary mechanical equipment |
| CN110674892A (en) * | 2019-10-24 | 2020-01-10 | 北京航空航天大学 | Fault feature screening method based on weighted multi-feature fusion and SVM classification |
| CN111076933A (en) * | 2019-12-14 | 2020-04-28 | 西安交通大学 | Method for establishing sensitive characteristic index set and identifying health state of machine tool spindle bearing |
| CN111896254A (en) * | 2020-08-10 | 2020-11-06 | 山东大学 | Fault prediction system and method for variable-speed variable-load large rolling bearing |
| CN112320520A (en) * | 2020-11-09 | 2021-02-05 | 浙江新再灵科技股份有限公司 | Elevator abnormal vibration detection method based on residual error analysis |
| CN113432886A (en) * | 2021-06-09 | 2021-09-24 | 中北大学 | Vehicle full-life cycle vibration impact testing method and device |
| CN113255840A (en) * | 2021-06-30 | 2021-08-13 | 长江存储科技有限责任公司 | Fault detection and classification method, device, system and storage medium |
| CN114659785A (en) * | 2021-12-27 | 2022-06-24 | 三一重能股份有限公司 | Fault detection method and device for transmission chain of wind driven generator |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109612729A (en) | A kind of malfunction recognition methods of port Machine Trolley Wheel Bearings | |
| CN108181107B (en) | The Wind turbines bearing mechanical method for diagnosing faults of meter and more class objects | |
| CN104712542B (en) | A kind of reciprocating compressor sensitive features based on Internet of Things are extracted and method for diagnosing faults | |
| CN110110768B (en) | Rolling bearing fault diagnosis method based on parallel feature learning and multiple classifiers | |
| CN107727395B (en) | A kind of Method for Bearing Fault Diagnosis based on full variation and uncompensation distance assessment | |
| CN104614179B (en) | A kind of gearbox of wind turbine state monitoring method | |
| CN105606363B (en) | A kind of Method for Bearing Fault Diagnosis adaptive based on domain | |
| CN110334764B (en) | Rotary machine intelligent fault diagnosis method based on integrated depth self-encoder | |
| CN104596767B (en) | Method for diagnosing and predicating rolling bearing based on grey support vector machine | |
| CN109781411B (en) | Bearing fault diagnosis method combining improved sparse filter and KELM | |
| CN104502126B (en) | A kind of high-speed train bogie method for diagnosing faults based on Modal Intervals | |
| CN110567720A (en) | method for diagnosing depth confrontation of fault of fan bearing under unbalanced small sample scene | |
| CN110276416A (en) | A kind of rolling bearing fault prediction technique | |
| Shi et al. | Fault diagnosis in a hydraulic directional valve using a two-stage multi-sensor information fusion | |
| CN111505424A (en) | Large experimental device power equipment fault diagnosis method based on deep convolutional neural network | |
| CN106441896A (en) | Characteristic vector extraction method for rolling bearing fault mode identification and state monitoring | |
| CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| CN109375010A (en) | Winding in Power Transformer method for diagnosing faults based on vibration distribution characteristic model | |
| CN110823576A (en) | Mechanical anomaly detection method based on generation of countermeasure network | |
| CN104807640A (en) | Method of detecting life state of spatial rolling bearing based on vibration-sensitive time-frequency characteristics | |
| CN105181336A (en) | Feature selection method for bearing fault diagnosis | |
| CN104316167B (en) | Structural response method for detecting abnormality under a kind of low signal-to-noise ratio | |
| CN104102726A (en) | Modified K-means clustering algorithm based on hierarchical clustering | |
| Du et al. | Intelligent turning tool monitoring with neural network adaptive learning | |
| CN106339720A (en) | Automobile engine failure detection method |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Liu Feng Inventor after: Zhai Jiayuan Inventor after: Jin Huidi Inventor after: Wang Guofeng Inventor after: An Hua Inventor before: Liu Feng Inventor before: Zhai Jiayuan Inventor before: Jin Huidi Inventor before: Wang Guofeng Inventor before: An Hua |
|
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190412 |