CN107506710A - A kind of rolling bearing combined failure extracting method - Google Patents
A kind of rolling bearing combined failure extracting method Download PDFInfo
- Publication number
- CN107506710A CN107506710A CN201710695141.3A CN201710695141A CN107506710A CN 107506710 A CN107506710 A CN 107506710A CN 201710695141 A CN201710695141 A CN 201710695141A CN 107506710 A CN107506710 A CN 107506710A
- Authority
- CN
- China
- Prior art keywords
- failure
- fault
- parameter
- deconvolution
- kurtosis
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a kind of rolling bearing combined failure extracting method, original vibration signal is filtered using maximal correlation kurtosis deconvolution as wave filter, by reasonably designing deconvolution parameter, primary signal is set to rise dimension after being handled by deconvolution into four groups of signals, four kinds of fault types are corresponded to respectively, and rise four groups of signals, one failure resonance bands of each correspondence that dimension obtains, single resonance bands signal is handled quickly to compose kurtosis figure, Fault-Sensitive frequency band can be accurately identified and be filtered, and then obtain the envelope spectrum of four groups of signals, the corresponding relation of fault characteristic frequency as obtained by contrasting four groups of signal envelope spectrums and theoretical calculation, the fault type of former combined failure signal can be differentiated.Meanwhile in the selection of maximal correlation kurtosis deconvolution parameter, the present invention takes the population optimization method in experience section, it is possible to increase the accuracy and adaptivity of parameter selection.
Description
Technical field
The present invention relates to a kind of bearing combined failure extracting method, more particularly to a kind of rolling bearing combined failure extraction side
Method, belong to bearing failure diagnosis technical field.
Background technology
Rolling bearing is one of widest parts of application in machine equipments, and whether its operation conditions well directly affects
The safe operation of plant equipment.In Practical Project, bearing is run under severe engineering specifications, various faults is often occurred and is deposited
Phenomenon.In recent years, it has been proposed that envelope demodulation, wavelet transformation, morphologic filtering the methods of mainly for single fault, to multiple
Fault reconstruction is closed to have difficulties.
It is special that the quick identification resonance bands composed kurtosis nomography can be adaptive and the envelope demodulation method that passes through extract failure
Sign, but in actual applications, the interference of multiple faults source and noise can cause to compose selection inaccuracy of the kurtosis figure to resonance bands.For
The accuracy of quick spectrum kurtosis analysis combined failure is improved, proposes one kind using maximal correlation kurtosis deconvolution as preposition processing,
Using fault characteristic frequency obtained by theoretical calculation as deconvolution periodical filtering, and then signal obtained by deconvolution is quickly composed high and steep
Spend the bearing combined failure diagnostic method of analysis.
The content of the invention
The technical problem to be solved in the present invention is to provide a kind of rolling bearing combined failure extracting method.
In order to solve the above technical problems, the technical solution adopted by the present invention is：
A kind of rolling bearing combined failure extracting method, comprises the following steps：
Step 1：Sample collection：The time-domain signal sample set of bearing running is obtained by vibration acceleration sensor；
Step 2：Obtain optimum solution convolutional filtering parameter：With adaptive optimization method in default deconvolution cycle optimizing
Optimizing index is turned to kurtosis value maximum in section and filter length optimizing section, seeks obtaining optimum solution convolutional filtering parameter combination
(T*,L*), T*For optimal deconvolution cycle, L*For optimal filter length；
Step 3：Filtering：Respectively using preset inner ring fault parameter, outer ring fault parameter, rolling element fault parameter, guarantor
Frame fault parameter is held, time-domain signal sample set is filtered under the conditions of filtering parameter is optimized, is obtained and inner ring failure, outer ring event
The corresponding deconvolution filtering output data of barrier, rolling element failure, retainer failure；
Step 4：Determine fault type：Respectively pair with inner ring failure, outer ring failure, rolling element failure, retainer failure pair
The output data answered carries out quick spectrum kurtosis analysis, and resonance centre frequency and bandwidth are determined by quickly composing kurtosis figure, then with altogether
Center of percussion frequency of heart and pair corresponding defeated with inner ring failure, outer ring failure, rolling element failure, retainer failure respectively with a width of parameter
Go out data and carry out quick spectrum kurtosis filtering, extract the envelope spectrum frequecy characteristic of corresponding output data, respectively calculating and theoretical calculation
The correlation of fault characteristic frequency, according to fault type corresponding to correlation prediction time-domain signal sample set.
Center of optimal deconvolution cycle in the step 2ForfsFor sample frequency, f*For fault signature frequency
Rate, deconvolution cycle optimizing section areFilter length optimizing section [50,300].
The time-domain signal sample set corresponds to a kind of fault type, and fault type corresponding to maximum correlation is time-domain signal
Fault type corresponding to sample set.
The time-domain signal sample set corresponds to more than one fault types, whether is more than default corresponding failure according to correlation
Relevance threshold judges its corresponding fault type.
The filtering parameter that optimizes corresponding with inner ring failure, outer ring failure, rolling element failure, retainer failure is respectively pre-
Asked under the conditions of the inner ring fault parameter put, outer ring fault parameter, rolling element fault parameter, retainer fault parameter.
The optimum solution convolutional filtering parameter is using population optimization method in default deconvolution cycle optimizing section
And optimizing is maximized with kurtosis value in filter length optimizing section and asked for.
Using having technical effect that acquired by above-mentioned technical proposal：
1st, the present invention can accurately identify Fault-Sensitive frequency band and be filtered, by contrasting four groups of signal envelope spectrums and reason
By the corresponding relation for calculating gained fault characteristic frequency, the fault type of former combined failure signal can be differentiated.
2nd, the present invention takes the population optimization method in experience section to select maximal correlation kurtosis deconvolution parameter, can
Improve the accuracy and adaptivity of parameter selection.
Brief description of the drawings
The present invention is further detailed explanation with reference to the accompanying drawings and detailed description.
Fig. 1 is flow chart；
Fig. 2 is the time-domain signal sample set of the embodiment of the present invention；
Fig. 3 is the deconvolution filtering output data corresponding with inner ring failure of the embodiment of the present invention；
Fig. 4 is the deconvolution filtering output data corresponding with outer ring failure of the embodiment of the present invention；
Fig. 5 is the deconvolution filtering output data corresponding with rolling element failure of the embodiment of the present invention；
Fig. 6 is the deconvolution filtering output data corresponding with retainer failure of the embodiment of the present invention；
Fig. 7 is the quick spectrum kurtosis of the deconvolution filtering output data corresponding with inner ring failure of the embodiment of the present invention
Figure；
Fig. 8 is the quick spectrum kurtosis of the deconvolution filtering output data corresponding with outer ring failure of the embodiment of the present invention
Figure；
Fig. 9 is the quick spectrum kurtosis of the deconvolution filtering output data corresponding with rolling element failure of the embodiment of the present invention
Figure；
Figure 10 is that the quickly spectrum of the deconvolution filtering output data corresponding with retainer failure of the embodiment of the present invention is high and steep
Degree figure；
Figure 11 is that the output data corresponding with inner ring failure of the embodiment of the present invention carries out quick spectrum kurtosis filtering output number
According to；
Figure 12 is that the output data corresponding with outer ring failure of the embodiment of the present invention carries out quick spectrum kurtosis filtering output number
According to；
Figure 13 is that the output data corresponding with rolling element failure of the embodiment of the present invention carries out quick spectrum kurtosis filtering output
Data；
Figure 14 is that the output data corresponding with retainer failure of the embodiment of the present invention carries out quick spectrum kurtosis filtering output
Data；
Figure 15 is the envelope spectrum signal corresponding with inner ring failure of the embodiment of the present invention；
Figure 16 is the envelope spectrum signal corresponding with outer ring failure of the embodiment of the present invention；
Figure 17 is the envelope spectrum signal corresponding with rolling element failure of the embodiment of the present invention；
Figure 18 is the envelope spectrum signal corresponding with retainer failure of the embodiment of the present invention.
Embodiment
Embodiment 1：
A kind of rolling bearing combined failure extracting method, comprises the following steps：
Step 1：Sample collection：The time-domain signal sample set of bearing running is obtained by vibration acceleration sensor；
Step 2：Obtain optimum solution convolutional filtering parameter：With adaptive optimization method in default deconvolution cycle optimizing
Optimizing index is turned to kurtosis value maximum in section and filter length optimizing section, seeks obtaining optimum solution convolutional filtering parameter combination
(T*,L*), T*For center of optimal deconvolution cycle, L*For optimal filter length；
Step 3：Filtering：Respectively using preset inner ring fault parameter, outer ring fault parameter, rolling element fault parameter, guarantor
Frame fault parameter is held, time-domain signal sample set is filtered under the conditions of filtering parameter is optimized, is obtained and inner ring failure, outer ring event
The corresponding deconvolution filtering output data of barrier, rolling element failure, retainer failure；
Step 4：Determine fault type：Respectively pair with inner ring failure, outer ring failure, rolling element failure, retainer failure pair
The output data answered carries out quick spectrum kurtosis analysis, and resonance centre frequency and bandwidth are determined by quickly composing kurtosis figure, then with altogether
Center of percussion frequency of heart and pair corresponding defeated with inner ring failure, outer ring failure, rolling element failure, retainer failure respectively with a width of parameter
Go out data and carry out quick spectrum kurtosis filtering, extract the envelope spectrum frequecy characteristic of corresponding output data, respectively calculating and theoretical calculation
The correlation of fault characteristic frequency, according to fault type corresponding to correlation prediction time-domain signal sample set.
Center of optimal deconvolution cycle in the step 2ForfsFor sample frequency, f*For fault signature frequency
Rate, deconvolution cycle optimizing section areFilter length optimizing section [50,300].
The time-domain signal sample set corresponds to a kind of fault type, and fault type corresponding to maximum correlation is time-domain signal
Fault type corresponding to sample set.
The time-domain signal sample set corresponds to more than one fault types, whether is more than default corresponding failure according to correlation
Relevance threshold judges its corresponding fault type.
The filtering parameter that optimizes corresponding with inner ring failure, outer ring failure, rolling element failure, retainer failure is respectively pre-
Inner ring fault parameter, outer ring fault parameter, rolling element fault parameter, the retainer fault parameter put, optimizing filtering parameter
Under the conditions of ask for.
The optimum solution convolutional filtering parameter is using population optimization method in default deconvolution cycle optimizing section
And optimizing is maximized with kurtosis value in filter length optimizing section and asked for.
It is real in QPZZ bearing fault simulations in order to verify validity of this method to strong background noise lower bearing fault reconstruction
Test on platform and complete rolling bearing inner ring, outer ring combined failure simulated experiment.Experiment uses 6205E bearings, uses wire cutting machine
Deep 1.5, wide 0.2mm groove is respectively processed on bearing inner race, outer ring to simulate bearing combined failure.Using data collecting card
Vibration signal is gathered by the acceleration transducer on bearing block.Wherein sample frequency 12800Hz, motor speed 1466r/
min。
Bearing fault characteristics frequency is calculated as：
Wherein：fiFor inner ring fault characteristic frequency；foFor outer ring fault characteristic frequency；fballFor rolling element failure
Characteristic frequency；fcageFor retainer fault characteristic frequency.
Deconvolution cycle center under theoretical calculation different faults
Toi=fs/fi=12800/132.2=96.8
Too=fs/fo=12800/87.7=146.0
Toball=fs/fball=12800/57.9=221.1
Tocage=fs/fcage=12800/9.8=1306.1 (2)
Wherein, ToiFor inner ring failure deconvolution cycle optimizing center；TooFor outer ring failure deconvolution optimizing center；Toball
For rolling element failure deconvolution optimizing center；TocageFor retainer failure deconvolution optimizing center.
Using population optimizing algorithm seek under different faults deconvolution optimal parameter combine, in the 15th generation time domain kurtosis most
Greatly, now parameter combination (96.6,120) is inner ring failure deconvolution optimal parameter.
Similarly, obtain outer ring, rolling element, retainer failure deconvolution optimal parameter combination (145,90), (225,110),
(1296,155).Respectively with four kinds of optimal parameter combination settings maximal correlation kurtosis deconvolution parameters under different faults type,
Original vibration signal is filtered, obtains output signal corresponding to four groups.
Envelope spectrum analysis, fault signature obtained by contrast theoretical calculation are carried out to four output signals obtained by step 4
Frequency, if including the fault characteristic frequency information in envelope spectrum, original vibration signal includes the trouble unit, if having no theoretical
Fault characteristic frequency, then not comprising the trouble unit, original vibration signal fault type is differentiated with this.It is visible interior in envelope spectrum
Circle, outer ring fault characteristic frequency (132Hz, 87.7Hz), not comprising rolling element, retainer fault characteristic frequency composition (57.9Hz,
9.8Hz), therefore it is diagnosed as Internal and external cycle combined failure.
The present invention is made an uproar under source interference and combined failure operating mode for quick spectrum kurtosis figure in processing, and multiple resonance bands are lacked
The shortcomings that weary sensitiveness, primary fault signal is transformed into by four groups of single fault signals with maximal correlation kurtosis deconvolution, to reach
Quick spectrum kurtosis figure is assisted to choose the purpose in failure resonance bands section.It is characterized in that using maximal correlation kurtosis deconvolution as
Wave filter filters to original vibration signal, by reasonably designing deconvolution parameter, after primary signal is handled by deconvolution
Dimension is risen into four groups of signals, corresponds to four kinds of fault types respectively, and rise one failure resonance of each correspondence of four groups of signals that dimension obtains
Frequency band, single resonance bands signal is handled quickly to compose kurtosis figure, Fault-Sensitive frequency band can be accurately identified and be filtered, and then
The envelope spectrum of four groups of signals is obtained, the corresponding pass of fault characteristic frequency as obtained by four groups of signal envelopes spectrums of contrast with theoretical calculation
System, the fault type of former combined failure signal can be differentiated.Meanwhile in the selection of maximal correlation kurtosis deconvolution parameter, this
The population optimization method in experience section is taken in invention, it is possible to increase the accuracy and adaptivity of parameter selection.
Claims (6)
- A kind of 1. rolling bearing combined failure extracting method, it is characterised in that：Comprise the following steps：Step 1：Sample collection：The time-domain signal sample set of bearing running is obtained by vibration acceleration sensor；Step 2：Obtain optimum solution convolutional filtering parameter：With adaptive optimization method in default deconvolution cycle optimizing section And optimizing index is turned to kurtosis value maximum in filter length optimizing section, seek obtaining optimum solution convolutional filtering parameter combination (T*, L*), T*For optimal deconvolution cycle, L*For optimal filter length；Step 3：Filtering：Respectively using preset inner ring fault parameter, outer ring fault parameter, rolling element fault parameter, retainer Fault parameter, time-domain signal sample set is filtered under the conditions of filtering parameter is optimized, obtained and inner ring failure, outer ring failure, rolling The corresponding deconvolution filtering output data of kinetoplast failure, retainer failure；Step 4：Determine fault type：It is pair corresponding with inner ring failure, outer ring failure, rolling element failure, retainer failure respectively Output data carries out quick spectrum kurtosis analysis, and resonance centre frequency and bandwidth are determined by quickly composing kurtosis figure, then with resonance Frequency of heart and with a width of parameter respectively pair with inner ring failure, outer ring failure, rolling element failure, retainer failure is corresponding exports number According to quick spectrum kurtosis filtering is carried out, the envelope spectrum frequecy characteristic of corresponding output data is extracted, is calculated and theoretical calculation failure respectively The correlation of characteristic frequency, according to fault type corresponding to correlation prediction time-domain signal sample set.
- 2. rolling bearing combined failure extracting method according to claim 1, it is characterised in that：Center T of optimal deconvolution cycle in the step 2o*For To*=fs/f*, fsFor sample frequency, f*For failureCharacteristic frequency, deconvolution cycle optimizing section areFilter length optimizing section [50, 300]。
- 3. rolling bearing combined failure extracting method according to claim 1, it is characterised in that：The time-domain signal sample set corresponds to a kind of fault type, and fault type corresponding to maximum correlation is time-domain signal sample The corresponding fault type of collection.
- 4. rolling bearing combined failure extracting method according to claim 1, it is characterised in that：The time-domain signal sample set corresponds to more than one fault types, related according to whether correlation is more than default corresponding failure Its corresponding fault type of property threshold determination.
- 5. rolling bearing combined failure extracting method according to claim 1, it is characterised in that：The filtering parameter that optimizes corresponding with inner ring failure, outer ring failure, rolling element failure, retainer failure is respectively preset Asked under the conditions of inner ring fault parameter, outer ring fault parameter, rolling element fault parameter, retainer fault parameter.
- 6. rolling bearing combined failure extracting method according to claim 1, it is characterised in that：The optimum solution convolution Filtering parameter using population optimization method in default deconvolution cycle optimizing section and filter length optimizing section with Kurtosis value maximizes optimizing and asked for.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710695141.3A CN107506710A (en) | 2017-08-15 | 2017-08-15 | A kind of rolling bearing combined failure extracting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710695141.3A CN107506710A (en) | 2017-08-15 | 2017-08-15 | A kind of rolling bearing combined failure extracting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107506710A true CN107506710A (en) | 2017-12-22 |
Family
ID=60690912
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710695141.3A Pending CN107506710A (en) | 2017-08-15 | 2017-08-15 | A kind of rolling bearing combined failure extracting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107506710A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108171263A (en) * | 2017-12-26 | 2018-06-15 | 合肥工业大学 | Based on the Fault Diagnosis of Roller Bearings for improving variation mode decomposition and extreme learning machine |
| CN109596354A (en) * | 2018-12-21 | 2019-04-09 | 电子科技大学 | Band-pass filtering method based on the identification of adaptive resonance frequency band |
| CN109682601A (en) * | 2019-03-04 | 2019-04-26 | 北京天泽智云科技有限公司 | The initial failure recognition methods of rolling bearing under a kind of variable speed operating condition |
| CN109916626A (en) * | 2019-03-14 | 2019-06-21 | 华北电力大学（保定） | The method and terminal device that rolling bearing combined failure determines |
| CN110173439A (en) * | 2019-05-29 | 2019-08-27 | 浙江大学 | A kind of nascent recognition methods of pump cavitation based on balanced squared envelope spectrum |
| CN110261108A (en) * | 2019-01-18 | 2019-09-20 | 北京化工大学 | Bearing fault method of identification when specified operating based on CNN color property figure |
| CN110647136A (en) * | 2019-09-29 | 2020-01-03 | 华东交通大学 | Composite fault detection and separation method for traction motor driving system |
| CN111678698A (en) * | 2020-06-17 | 2020-09-18 | 沈阳建筑大学 | Rolling bearing fault detection method based on sound and vibration signal fusion |
| CN112001314A (en) * | 2020-08-25 | 2020-11-27 | 江苏师范大学 | Early fault detection method for variable speed hoist |
| CN112484999A (en) * | 2020-12-24 | 2021-03-12 | 温州大学 | Rolling bearing composite fault diagnosis method and device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105092249A (en) * | 2015-09-22 | 2015-11-25 | 山东理工大学 | Rolling bearing fault diagnosis method based on Gabor filter |
-
2017
- 2017-08-15 CN CN201710695141.3A patent/CN107506710A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105092249A (en) * | 2015-09-22 | 2015-11-25 | 山东理工大学 | Rolling bearing fault diagnosis method based on Gabor filter |
Non-Patent Citations (4)
| Title |
|---|
| 唐贵基 等: "基于包络谱稀疏度和最大相关峭度解卷积的滚动轴承早期故障诊断方法", 《中国机械工程》 * |
| 唐贵基 等: "自适应最大相关峭度解卷积方法及其在轴承早期故障诊断中的应用", 《中国电机工程学报》 * |
| 王晓龙 等: "基于变分模态分解和1.5 维谱的轴承早期故障诊断方法", 《电力自动化设备》 * |
| 钟先友 等: "基于MCKD和重分配小波尺度谱的旋转机械复合故障诊断研究", 《振动与冲击》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108171263A (en) * | 2017-12-26 | 2018-06-15 | 合肥工业大学 | Based on the Fault Diagnosis of Roller Bearings for improving variation mode decomposition and extreme learning machine |
| CN109596354B (en) * | 2018-12-21 | 2020-06-09 | 电子科技大学 | Band-pass filtering method based on self-adaptive resonance frequency band identification |
| CN109596354A (en) * | 2018-12-21 | 2019-04-09 | 电子科技大学 | Band-pass filtering method based on the identification of adaptive resonance frequency band |
| CN110261108A (en) * | 2019-01-18 | 2019-09-20 | 北京化工大学 | Bearing fault method of identification when specified operating based on CNN color property figure |
| CN109682601A (en) * | 2019-03-04 | 2019-04-26 | 北京天泽智云科技有限公司 | The initial failure recognition methods of rolling bearing under a kind of variable speed operating condition |
| CN109916626A (en) * | 2019-03-14 | 2019-06-21 | 华北电力大学（保定） | The method and terminal device that rolling bearing combined failure determines |
| CN110173439A (en) * | 2019-05-29 | 2019-08-27 | 浙江大学 | A kind of nascent recognition methods of pump cavitation based on balanced squared envelope spectrum |
| CN110173439B (en) * | 2019-05-29 | 2020-05-08 | 浙江大学 | Pump cavitation primary identification method based on balanced square envelope spectrum |
| CN110647136A (en) * | 2019-09-29 | 2020-01-03 | 华东交通大学 | Composite fault detection and separation method for traction motor driving system |
| CN110647136B (en) * | 2019-09-29 | 2021-01-05 | 华东交通大学 | Composite fault detection and separation method for traction motor driving system |
| CN111678698A (en) * | 2020-06-17 | 2020-09-18 | 沈阳建筑大学 | Rolling bearing fault detection method based on sound and vibration signal fusion |
| CN111678698B (en) * | 2020-06-17 | 2022-03-04 | 沈阳建筑大学 | Rolling bearing fault detection method based on sound and vibration signal fusion |
| CN112001314A (en) * | 2020-08-25 | 2020-11-27 | 江苏师范大学 | Early fault detection method for variable speed hoist |
| CN112484999A (en) * | 2020-12-24 | 2021-03-12 | 温州大学 | Rolling bearing composite fault diagnosis method and device |
| CN112484999B (en) * | 2020-12-24 | 2022-04-15 | 温州大学 | Rolling bearing composite fault diagnosis method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107506710A (en) | A kind of rolling bearing combined failure extracting method | |
| CN111046945B (en) | Fault type and damage degree diagnosis method based on combined convolutional neural network | |
| CN112254964A (en) | Rolling bearing fault diagnosis method based on rapid multi-scale convolution neural network | |
| CN109635334A (en) | Fault Diagnosis of Roller Bearings, system and medium based on particle group optimizing | |
| CN109932179B (en) | Rolling bearing fault detection method based on DS self-adaptive spectrum reconstruction | |
| CN110046476B (en) | Ternary binary fractal wavelet sparse diagnosis method for rolling bearing faults | |
| CN111238814A (en) | Rolling bearing fault diagnosis method based on short-time Hilbert transform | |
| CN111122161B (en) | Variable working condition bearing fault diagnosis method based on fast kurtogram and deep residual learning | |
| CN109765055B (en) | Rolling bearing fault detection method and system based on EWT, spectrum effective value and KNN | |
| CN106096313B (en) | A kind of envelope Analysis Method based on unusual spectral factorization and spectrum kurtosis | |
| CN111238813B (en) | Method for extracting fault features of rolling bearing under strong interference | |
| CN110555243B (en) | Two-dimensional map construction method for vibration information of machine tool spindle in milling process | |
| CN106096200B (en) | A kind of envelope Analysis Method based on wavelet decomposition and spectrum kurtosis | |
| CN114004256A (en) | Fault diagnosis method for manufacturing equipment main bearing based on digital twin body | |
| CN113569990B (en) | Strong noise interference environment-oriented performance equipment fault diagnosis model construction method | |
| CN113532848A (en) | Fault diagnosis system for planetary gear box | |
| CN111076934A (en) | Method for diagnosing potential fault of bearing based on S transformation | |
| CN112733612A (en) | Cross-domain rotating machinery fault diagnosis model establishing method and application thereof | |
| CN115481666B (en) | Gearbox small sample fault diagnosis method, system and equipment | |
| CN111811819A (en) | Bearing fault diagnosis method and device based on machine learning | |
| CN111896260A (en) | NGAs synchronous optimization wavelet filter and MCKD bearing fault diagnosis method | |
| CN116089813A (en) | Wind turbine generator set transmission chain fault diagnosis method based on machine learning | |
| CN112857804A (en) | Rolling bearing fault diagnosis method, device, medium and computer equipment | |
| CN105954031B (en) | A kind of envelope Analysis Method based on unusual spectral factorization filtering | |
| CN106053060B (en) | A kind of envelope Analysis Method that filtering is decomposed based on nonlinear model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171222 |