CN110132596A - A method of the rolling bearing fault diagnosis based on wavelet packet and GWO-SVM - Google Patents
A method of the rolling bearing fault diagnosis based on wavelet packet and GWO-SVM Download PDFInfo
- Publication number
- CN110132596A CN110132596A CN201910333310.8A CN201910333310A CN110132596A CN 110132596 A CN110132596 A CN 110132596A CN 201910333310 A CN201910333310 A CN 201910333310A CN 110132596 A CN110132596 A CN 110132596A
- Authority
- CN
- China
- Prior art keywords
- wolf
- svm
- prey
- gwo
- rolling bearing
- 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
- 238000005096 rolling process Methods 0.000 title claims abstract description 42
- 238000003745 diagnosis Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 title claims abstract description 15
- 241000282461 Canis lupus Species 0.000 claims abstract description 81
- 238000012706 support-vector machine Methods 0.000 claims abstract description 32
- 238000012360 testing method Methods 0.000 claims abstract description 21
- 238000005457 optimization Methods 0.000 claims abstract description 13
- 230000001133 acceleration Effects 0.000 claims abstract description 12
- 238000005259 measurement Methods 0.000 claims abstract description 9
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 8
- 241000282421 Canidae Species 0.000 claims description 6
- 241001269238 Data Species 0.000 claims description 5
- 230000006978 adaptation Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims 1
- 235000013399 edible fruits Nutrition 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003993 interaction Effects 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 relates to a kind of methods of rolling bearing fault diagnosis based on wavelet packet and GWO-SVM, belong to the field of mechanical fault diagnosis.Different vibration signals of the present invention using acceleration transducer measurement rolling bearing under inner ring failure, outer ring failure, rolling element failure and normal condition, then 3 layers of decomposition are carried out to signal by wavelet packet, calculates characteristic of the energy of the 3rd layer of 8 node as signal.After extracting its feature, characteristic parameter is input in the support vector machines (Support Vector Machine, SVM) by grey wolf algorithm optimization and is trained, the fault diagnosis model based on GWO-SVM is obtained.Finally test data is input in trained model, finally obtains the fault type of test data.The experimental results showed that grey wolf algorithm has significant raising to the accuracy of fault identification.With fault diagnosis precision, training time and testing time are standard, have higher accuracy and shorter runing time by the svm classifier of GWO algorithm optimization.
Description
Technical field
The present invention relates to a kind of methods of rolling bearing fault diagnosis based on wavelet packet and GWO-SVM, belong to mechanical event
Hinder the scope of diagnosis.
Background technique
Rolling bearing is the core of all industrial equipments, during the sliding friction between axis and axle bed is converted operation by it
Rolling friction.A kind of industrial part of energy loss and operating status rate is reduced with this.Equipment is all located in industrial environment
In the state of high speed, heavy duty and high-intensity magnetic field, rolling bearing is as an indispensable part, and the stability of operating status is to machine
The performance of tool system has the influence for being difficult to ignore.In this case, rolling bearing inner ring, outer ring are timely and accurately diagnosed to be
It is of crucial importance to the operation of mechanical equipment with the failure of rolling element.
In fault diagnosis, the parameter selection of support vector machines (SVM) and the nicety of grading of vector machine itself have very high point
System.For this problem, Swarm Intelligent Algorithm can be used to optimize its parameter, to improve the accurate of fault diagnosis
Property.The working principle of Swarm Intelligent Algorithm is the interaction showed by simulating various macroscopical or microcosmic groups,
Using between group and group, between individual and individual correlation, obtained by continuous feedback information and be best suited for asking
The method of topic.But the accuracy rate of rolling bearing fault is lower in the prior art and its Diagnostic Time is longer.
Summary of the invention
The technical problem to be solved by the present invention is to propose a kind of fault diagnosis based on wavelet packet and GWO-SVM rolling bearing
Method the accurate of diagnosis rolling bearing fault is improved by the penalty coefficient c and kernel function radius sigma of Support Vector Machines Optimized
Rate and Diagnostic Time.
The technical solution adopted by the present invention is that: a kind of side of the rolling bearing fault diagnosis based on wavelet packet and GWO-SVM
Method, using acceleration transducer measurement rolling bearing under inner ring failure, outer ring failure, rolling element failure and normal condition not
With vibration signal, then 3 layers of decomposition are carried out to each signal of measurement by wavelet packet respectively, calculate each signal the
The energy of 3 layers of 8 node and characteristic as signal；After extracting its feature, by characteristic parameter be input to by
It is trained, is obtained based on GWO- in the support vector machines (Support Vector Machine, SVM) of grey wolf algorithm optimization
The fault diagnosis model of SVM.Finally test data is input in trained model, finally obtains the failure classes of test data
Type.
Specific step is as follows:
(1) acceleration transducer is mounted on the driving end of rolling bearing.Vibration acceleration signal is by 16 channel datas
Recorder collects.Drive end bearing failure sample frequency is 12kHz.The revolving speed of rolling bearing is set as 1730r/min.Point
Not Ce Liang different vibration signals of the rolling bearing under inner ring failure, outer ring failure, rolling element failure and normal condition, then
3 layers of decomposition are carried out respectively by each signal of wavelet packet to measurement, calculate the energy of the 3rd layer of 8 node of each signal
And as the characteristic of signal.
(2) after the feature for extracting training data, characteristic parameter is input to by the supporting vector of grey wolf algorithm optimization
It is trained in machine (Support Vector Machine, SVM), wherein grey wolf algorithmic procedure is as follows: assuming that t is current iteration
Number, XpIt (t) is t moment prey position vector, X (t) is t moment wolf pack position vector, then the distance between wolf pack and prey D
Are as follows:
D=| CXP(t)-X(t)| (1)
After obtaining wolf pack and prey distance, wolf pack needs to adjust the position of oneself in due course, and formula is as follows:
X (t+1)=XP(t)-A·D (2)
Wherein, X (t+1) is t+1 moment wolf pack position vector, and A, C are coefficient vector, by the available A of following formula,
The value of C
A=2ar1-a (3)
C=2r2 (4)
Wherein, r1,r2The random vector of ∈ [0,1].A is convergence factor, with the increase of the number of iterations it is linear from 2
It is decremented to 0.The expression formula of a
Wherein, max is maximum number of iterations.After head wolf determines prey general orientation, other subordinate wolves pair will be led
Prey is rounded up and hunt, and using the positional relationship between wolf pack individual, prey position is determined more accurately, is finally attacked.
It is as follows that wolf pack surrounds and seize prey change in location formula:
Dα=| C1Xα(t)-X(t)| (6)
Dβ=| C2Xβ(t)-X(t)| (7)
Dδ=| C3Xδ(t)-X(t) (8)
X1=Xα-A1Dα
X2=Xβ-A2Dβ (9)
X3=Xδ-A3Dδ
Wherein Dα,Dβ,DδThe distance between respectively α, β, δ wolf and prey, A1,A2,A3And C1,C2,C3Respectively α, β, δ
Coefficient vector, Xα(t),Xβ(t),XδIt (t) is t moment prey position, X1,X2,X3Respectively wolf pack vector position, Xα,Xβ,Xδ
Respectively prey vector position.When | A | when > 1, wolf pack will increase the area in hunting region, then search for prey in larger scope,
It carries out the overall situation and searches element, convergence rate is accelerated；When | A | when < 1, wolf pack will shrink the area in hunting region, determine the position of prey
It sets, i.e. progress local search, slows down convergence rate.The reason of wolf pack algorithm is easily trapped into locally optimal solution is exactly when wolf pack changes
When becoming attack direction, the position of prey can be missed, prey is caused to lose.Penalty coefficient c, the kernel function of SVM are initialized first
The position of radius sigma and wolf pack；Secondly by the position for traversing all grey wolves, optimal individual adaptation degree α is obtained, remaining each self-contained
For β, δ and ω group.Position individual in wolf pack can be updated according to above formula.The fitness of every wolf in a new location is carried out
It calculates and is compared with last iteration fitness, if new fitness is higher than, new fitness replaces original work
For adaptive optimal control degree, and new wolf position substitutes original position；If be not above, original fitness is remained unchanged.Such as
Fruit completes largest loop requirement, then training stops, and exports the position of α wolf and β wolf, exactly optimal SVM parameter c and σ
Value；Continue update wolf pack position if not completing largest loop uses α, β to establish SVM as c and σ respectively, by training data
Operation is substituted into, GWO-SVM training pattern is obtained.
(3) test data is input in trained GWO-SVM diagnostic model, obtains the classification results of test data.
The beneficial effects of the present invention are:
(1) feature extraction is carried out to the data being collected into using wavelet packet, extraction feature is obvious, method high reliablity；
(2) it is optimized using parameter of the grey wolf algorithm to support vector machines, improves the identification of rolling bearing fault diagnosis
Rate and Diagnostic Time.
Detailed description of the invention
Fig. 1 is diagnostic model schematic diagram of the present invention；
Fig. 2 is that wolf pack of the present invention surrounds and seize change in location；
Fig. 3 is support vector machines network structure of the present invention；
Fig. 4 is that inventive algorithm improves SVM fitness curve；
Fig. 5 is GWO-SVM category of model accuracy of the present invention；
Fig. 6 is test set classification chart of the present invention.
Specific embodiment
In the following with reference to the drawings and specific embodiments, the invention will be further described
Embodiment 1: as shown in figs 1 to 6, a kind of side of the rolling bearing fault diagnosis based on wavelet packet and GWO-SVM
Method, include the following steps: using acceleration transducer measurement rolling bearing inner ring failure, outer ring failure, rolling element failure and
Then different vibration signals under normal condition carry out 3 layers of decomposition, meter to each signal of measurement by wavelet packet respectively
Calculate the energy of the 3rd layer of 8 node of each signal and the characteristic as signal；It, will be special after extracting its feature
Sign parameter, which is input in the support vector machines (Support Vector Machine, SVM) by grey wolf algorithm optimization, to be trained,
Obtain the fault diagnosis model based on GWO-SVM.Finally test data is input in trained model, finally obtains test
The fault type of data.
Specific steps are as follows:
(1) acceleration transducer is mounted on the driving end of rolling bearing.Vibration acceleration signal is by 16 channel datas
Recorder collects.Drive end bearing failure sample frequency is 12kHz.The revolving speed of rolling bearing is set as 1730r/min.Point
Not Ce Liang different vibration signals of the rolling bearing under inner ring failure, outer ring failure, rolling element failure and normal condition, pass through
Wavelet packet carries out 3 layers of decomposition to signal, calculates characteristic of the energy of the 3rd layer of 8 node as signal.
(2) after the feature for extracting training data, characteristic parameter is input to by the supporting vector of grey wolf algorithm optimization
It is trained in machine (Support Vector Machine, SVM), wherein grey wolf algorithmic procedure is as follows: assuming that t is current iteration
Number, XpIt (t) is t moment prey position vector, X (t) is t moment wolf pack position vector, then the distance between wolf pack and prey D
Are as follows:
D=| CXP(t)-X(t)| (1)
After obtaining wolf pack and prey distance, wolf pack needs to adjust the position of oneself in due course, and formula is as follows:
X (t+1)=XP(t)-A·D (2)
Wherein, X (t+1) is t+1 moment wolf pack position vector, and A, C are coefficient vector, by the available A of following formula,
The value of C
A=2ar1-a (3)
C=2r2 (4)
Wherein, r1,r2The random vector of ∈ [0,1].A is convergence factor, with the increase of the number of iterations it is linear from 2
It is decremented to 0.Expression formula
Wherein, max is maximum number of iterations.After head wolf determines prey general orientation, other subordinate wolves pair will be led
Prey is rounded up and hunt, and using the positional relationship between wolf pack individual, prey position is determined more accurately, is finally attacked.
It is as follows that wolf pack surrounds and seize prey change in location formula:
Dα=| C1Xα(t)-X(t)| (6)
Dβ=| C2Xβ(t)-X(t)| (7)
Dδ=| C3Xδ(t)-X(t) (8)
X1=Xα-A1Dα
X2=Xβ-A2Dβ (9)
X3=Xδ-A3Dδ
Wherein Dα,Dβ,DδThe distance between respectively α, β, δ wolf and prey, A1,A2,A3And C1,C2,C3Respectively α, β, δ
Coefficient vector, Xα(t),Xβ(t),XδIt (t) is t moment prey position, X1,X2,X3Respectively wolf pack vector position, Xα,Xβ,Xδ
Respectively prey vector position.When | A | when > 1, wolf pack will increase the area in hunting region, then search for prey in larger scope,
It carries out the overall situation and searches element, convergence rate is accelerated；When | A | when < 1, wolf pack will shrink the area in hunting region, determine the position of prey
It sets, i.e. progress local search, slows down convergence rate.The reason of wolf pack algorithm is easily trapped into locally optimal solution is exactly when wolf pack changes
When becoming attack direction, the position of prey can be missed, prey is caused to lose.Penalty coefficient c, the kernel function of SVM are initialized first
The position of radius sigma and wolf pack；Secondly by the position for traversing all grey wolves, optimal individual adaptation degree α is obtained, remaining each self-contained
For β, δ and ω group.Position individual in wolf pack can be updated according to above formula.The fitness of every wolf in a new location is carried out
It calculates and is compared with last iteration fitness, if new fitness is higher than, new fitness replaces original work
For adaptive optimal control degree, and new wolf position substitutes original position；If be not above, original fitness is remained unchanged.Such as
Fruit completes largest loop requirement, then training stops, and exports the position of α wolf and β wolf, exactly optimal SVM parameter c and σ
Value；Continue update wolf pack position if not completing largest loop uses α, β to establish SVM as c and σ respectively, by training data
Operation is substituted into, GWO-SVM training pattern is obtained.
(3) test data is input in trained GWO-SVM diagnostic model, obtains the classification results of test data.
The principle of the present invention is: carrying out fault diagnosis using grey wolf algorithm optimization support vector machines, essence is to utilize ash
The penalty coefficient c and kernel function radius sigma of wolf algorithm optimization support vector machines obtain GWO-SVM diagnosis by inputting training data
Model, so as to improve the discrimination and runing time of rolling bearing fault diagnosis.
It is described in detail below with reference to specific example:
Now acceleration transducer is mounted on the driving end of rolling bearing.Vibration acceleration signal is remembered by 16 channel datas
Record instrument collects.Drive end bearing failure sample frequency is 12kHz.The revolving speed of rolling bearing is set as 1730r/min.Respectively
Measure different vibration signals of the rolling bearing under inner ring failure, outer ring failure, rolling element failure and normal condition.Through measuring
The size for obtaining every class data is 8*1200, wherein 8 be intrinsic dimensionality, 1200 be number of samples.Every class selects 800 sample conducts
Training, remaining 400 tests, therefore 4 class data share 3200 training samples, 1600 test samples.Pass through wavelet packet pair
Signal carries out 3 layers of decomposition, calculates characteristic of the energy of the 3rd layer of 8 node as signal.Pass through formula (1)-(9) simultaneously
SVM prediction model is established with the penalty coefficient c of grey wolf algorithm optimization support vector machines, kernel function radius sigma, is extracting 3200 instructions
After the feature for practicing data, characteristic parameter is input in the support vector machines by grey wolf algorithm optimization and is trained, base is obtained
In the fault diagnosis model of GWO-SVM.Last 1600 test datas are input in trained model, finally obtain test number
According to fault type.And the accuracy rate for calculating GWO-SVM diagnostic model is 91.93%, training time 0.4534s, test
Time is 0.0423s.
The experimental results showed that grey wolf algorithm has significant raising to the accuracy of fault identification.With fault diagnosis precision, training
Time and testing time are standard, have higher accuracy and shorter runing time by the svm classifier of GWO algorithm optimization.
Above in conjunction with attached drawing, the embodiment of the present invention is explained in detail, but the present invention is not limited to above-mentioned
Embodiment within the knowledge of a person skilled in the art can also be before not departing from present inventive concept
Put that various changes can be made.
Claims (2)
1. a kind of method of the rolling bearing fault diagnosis based on wavelet packet and GWO-SVM, it is characterised in that: including walking as follows
It is rapid: using acceleration transducer measurement rolling bearing under inner ring failure, outer ring failure, rolling element failure and normal condition not
With vibration signal, then 3 layers of decomposition are carried out to each signal of measurement by wavelet packet respectively, calculate each signal the
The energy of 3 layers of 8 node and characteristic as signal；After extracting its feature, by characteristic parameter be input to by
It is trained in the support vector machines of grey wolf algorithm optimization, obtains the fault diagnosis model based on GWO-SVM；It will finally survey
Examination data are input in trained model, finally obtain the fault type of test data.
2. a kind of method of rolling bearing fault diagnosis based on wavelet packet and GWO-SVM according to claim 1, special
Sign is: specific steps are as follows:
(1) acceleration transducer is mounted on the driving end of rolling bearing, vibration acceleration signal is recorded by 16 channel datas
Instrument collects, and drive end bearing failure sample frequency is 12kHz, and the revolving speed of rolling bearing is set as 1730r/min, surveys respectively
Different vibration signals of the rolling bearing under inner ring failure, outer ring failure, rolling element failure and normal condition are measured, are then passed through
Wavelet packet carries out 3 layers of decomposition to each signal of measurement respectively, calculates the energy of the 3rd layer of 8 node of each signal and incites somebody to action
Its characteristic as signal；
(2) after the feature for extracting training data, characteristic parameter is input to by the support vector machines of grey wolf algorithm optimization
In be trained, wherein grey wolf algorithmic procedure is as follows: assuming that t be current iteration number, XpIt (t) is t moment prey position vector,
X (t) is t moment wolf pack position vector, then the distance between wolf pack and prey D are as follows:
D=| CXP(t)-X(t)| (1)
After obtaining wolf pack and prey distance, wolf pack needs to adjust the position of oneself in due course, and formula is as follows:
X (t+1)=XP(t)-A·D (2)
Wherein, X (t+1) is t+1 moment wolf pack position vector, and A, C are coefficient vector, by the available A of following formula, C's
Value
A=2ar1-a (3)
C=2r2 (4)
Wherein, r1,r2The random vector of ∈ [0,1], a are convergence factor, are successively decreased as the increase of the number of iterations is linear from 2
To the expression formula of 0, a
Wherein, max is maximum number of iterations, after head wolf determines prey general orientation, other subordinate wolves will be led to prey
It rounds up and hunt, using the positional relationship between wolf pack individual, prey position is determined more accurately, is finally attacked, wolf pack
It is as follows to surround and seize prey change in location formula:
Dα=| C1Xα(t)-X(t)| (6)
Dβ=| C2Xβ(t)-X(t)| (7)
Dδ=| C3Xδ(t)-X(t) (8)
X1=Xα-A1Dα
X2=Xβ-A2Dβ (9)
X3=Xδ-A3Dδ
Wherein: Dα,Dβ,DδThe distance between respectively α, β, δ wolf and prey, A1,A2,A3And C1,C2,C3Respectively α, β, δ's is
Number vector, Xα(t),Xβ(t),XδIt (t) is t moment prey position, X1,X2,X3Respectively wolf pack vector position, Xα,Xβ,XδRespectively
For prey vector position, as | A | when > 1, wolf pack will increase the area in hunting region, then search for prey in larger scope, i.e., into
The row overall situation searches element, and convergence rate is accelerated；When | A | when < 1, wolf pack will shrink the area in hunting region, determine the position of prey, i.e.,
Carry out local search, slow down convergence rate, the reason of wolf pack algorithm is easily trapped into locally optimal solution exactly when wolf pack change into
Offense to when, the position of prey can be missed, prey is caused to lose, i.e., initialize the penalty coefficient c of SVM, kernel function radius sigma first
With the position of wolf pack；Secondly by the position for traversing all grey wolves, optimal individual adaptation degree α is obtained, remaining respectively becomes β, δ
With ω group, position individual in wolf pack can be updated according to above formula, and the fitness of every wolf in a new location is calculated
And it is compared with last iteration fitness, if new fitness is higher than originally, new fitness replaces original
As adaptive optimal control degree, and new wolf position substitutes original position；If be not above, original fitness is remained unchanged,
If completing largest loop requirement, it is exactly optimal SVM parameter c and σ that training, which stops, and exports the position of α wolf and β wolf
Value；Continue update wolf pack position if not completing largest loop uses α, β to establish SVM as c and σ respectively, will training number
It is run according to substituting into, obtains GWO-SVM training pattern；
(3) test data is input in trained GWO-SVM diagnostic model, obtains the classification results of test data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910333310.8A CN110132596A (en) | 2019-04-24 | 2019-04-24 | A method of the rolling bearing fault diagnosis based on wavelet packet and GWO-SVM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910333310.8A CN110132596A (en) | 2019-04-24 | 2019-04-24 | A method of the rolling bearing fault diagnosis based on wavelet packet and GWO-SVM |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110132596A true CN110132596A (en) | 2019-08-16 |
Family
ID=67571085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910333310.8A Pending CN110132596A (en) | 2019-04-24 | 2019-04-24 | A method of the rolling bearing fault diagnosis based on wavelet packet and GWO-SVM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110132596A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111024433A (en) * | 2019-12-30 | 2020-04-17 | 辽宁大学 | Industrial equipment health state detection method for optimizing support vector machine by improving wolf algorithm |
| CN111242005A (en) * | 2020-01-10 | 2020-06-05 | 西华大学 | Heart sound classification method based on improved wolf colony algorithm optimization support vector machine |
| CN111272429A (en) * | 2020-03-04 | 2020-06-12 | 贵州大学 | Bearing fault diagnosis method |
| CN111368892A (en) * | 2020-02-27 | 2020-07-03 | 合肥工业大学 | Generalized S transformation and SVM electric energy quality disturbance efficient identification method |
| CN111428418A (en) * | 2020-02-28 | 2020-07-17 | 贵州大学 | Bearing fault diagnosis method and device, computer equipment and storage medium |
| CN111563348A (en) * | 2020-04-10 | 2020-08-21 | 西安工程大学 | Transformer fault diagnosis method based on deep support vector machine |
| CN111603161A (en) * | 2020-05-28 | 2020-09-01 | 苏州小蓝医疗科技有限公司 | Electroencephalogram classification method |
| CN112052934A (en) * | 2020-09-08 | 2020-12-08 | 江南大学 | Motor bearing fault diagnosis method based on improved wolf optimization algorithm |
| CN112285541A (en) * | 2020-09-21 | 2021-01-29 | 南京理工大学 | Fault diagnosis method for current frequency conversion circuit |
| CN112288001A (en) * | 2020-10-28 | 2021-01-29 | 北京航空航天大学 | GWO oversampling-based high-speed rail brake system fault detection SVM method |
| CN112836604A (en) * | 2021-01-22 | 2021-05-25 | 合肥工业大学 | Rolling bearing fault diagnosis and classification method, system and equipment based on VMD-SSAE and storage medium thereof |
| CN113670609A (en) * | 2021-07-21 | 2021-11-19 | 广州大学 | Fault detection method, system, device and medium based on wolf optimization algorithm |
| CN113917287A (en) * | 2021-11-22 | 2022-01-11 | 国家电网有限公司 | Substation bus joint discharge heating fault monitoring system |
| CN113923104A (en) * | 2021-12-07 | 2022-01-11 | 南京信息工程大学 | Network fault diagnosis method, equipment and storage medium based on wavelet neural network |
| CN114781577A (en) * | 2022-05-06 | 2022-07-22 | 安徽理工大学 | Buck circuit fault diagnosis method based on VMD-DCNN-SVM |
| CN115032270A (en) * | 2022-06-01 | 2022-09-09 | 北京科技大学 | Method and device for quantitatively identifying damage state of building curtain wall based on machine learning algorithm |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102183366A (en) * | 2011-03-08 | 2011-09-14 | 上海大学 | Device and method for vibration measurement and failure analysis of rolling bearing |
| CN103542929A (en) * | 2013-05-20 | 2014-01-29 | 西北工业大学 | Method for extracting signal features of bearings on basis of wavelet packet energy matrixes |
| CN103900816A (en) * | 2014-04-14 | 2014-07-02 | 上海电机学院 | Method for diagnosing bearing breakdown of wind generating set |
| CN104655423A (en) * | 2013-11-19 | 2015-05-27 | 北京交通大学 | Rolling bearing fault diagnosis method based on time-frequency domain multidimensional vibration feature fusion |
| CN104729853A (en) * | 2015-04-10 | 2015-06-24 | 华东交通大学 | Rolling bearing performance degradation evaluation device and method |
| CN106022517A (en) * | 2016-05-17 | 2016-10-12 | 温州大学 | Risk prediction method and device based on nucleus limit learning machine |
| CN106092578A (en) * | 2016-07-15 | 2016-11-09 | 西安交通大学 | A kind of machine tool mainshaft bearing confined state online test method based on wavelet packet and support vector machine |
| CN106355192A (en) * | 2016-08-16 | 2017-01-25 | 温州大学 | Support vector machine method based on chaos and grey wolf optimization |
| CN107084854A (en) * | 2017-04-17 | 2017-08-22 | 四川大学 | Self-adapting random resonant Incipient Fault Diagnosis method based on grey wolf optimized algorithm |
| CN107909141A (en) * | 2017-11-27 | 2018-04-13 | 温州大学 | A kind of data analysing method and device based on grey wolf optimization algorithm |
| CN108520272A (en) * | 2018-03-22 | 2018-09-11 | 江南大学 | A kind of semi-supervised intrusion detection method improving blue wolf algorithm |
| CN109612731A (en) * | 2019-01-22 | 2019-04-12 | 昆明理工大学 | Fault Diagnosis of Roller Bearings based on Harmonic wavelet packet and IAGA-SVM |
-
2019
- 2019-04-24 CN CN201910333310.8A patent/CN110132596A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102183366A (en) * | 2011-03-08 | 2011-09-14 | 上海大学 | Device and method for vibration measurement and failure analysis of rolling bearing |
| CN103542929A (en) * | 2013-05-20 | 2014-01-29 | 西北工业大学 | Method for extracting signal features of bearings on basis of wavelet packet energy matrixes |
| CN104655423A (en) * | 2013-11-19 | 2015-05-27 | 北京交通大学 | Rolling bearing fault diagnosis method based on time-frequency domain multidimensional vibration feature fusion |
| CN103900816A (en) * | 2014-04-14 | 2014-07-02 | 上海电机学院 | Method for diagnosing bearing breakdown of wind generating set |
| CN104729853A (en) * | 2015-04-10 | 2015-06-24 | 华东交通大学 | Rolling bearing performance degradation evaluation device and method |
| CN106022517A (en) * | 2016-05-17 | 2016-10-12 | 温州大学 | Risk prediction method and device based on nucleus limit learning machine |
| CN106092578A (en) * | 2016-07-15 | 2016-11-09 | 西安交通大学 | A kind of machine tool mainshaft bearing confined state online test method based on wavelet packet and support vector machine |
| CN106355192A (en) * | 2016-08-16 | 2017-01-25 | 温州大学 | Support vector machine method based on chaos and grey wolf optimization |
| CN107084854A (en) * | 2017-04-17 | 2017-08-22 | 四川大学 | Self-adapting random resonant Incipient Fault Diagnosis method based on grey wolf optimized algorithm |
| CN107909141A (en) * | 2017-11-27 | 2018-04-13 | 温州大学 | A kind of data analysing method and device based on grey wolf optimization algorithm |
| CN108520272A (en) * | 2018-03-22 | 2018-09-11 | 江南大学 | A kind of semi-supervised intrusion detection method improving blue wolf algorithm |
| CN109612731A (en) * | 2019-01-22 | 2019-04-12 | 昆明理工大学 | Fault Diagnosis of Roller Bearings based on Harmonic wavelet packet and IAGA-SVM |
Non-Patent Citations (2)
| Title |
|---|
| 郭振洲 等: ""基于灰狼算法的改进研究"", 《计算机应用研究》 * |
| 雷俊辉: ""基于多特征融合和IGWO-MSVM的矿用齿轮箱故障诊断研究"", 《中国优秀硕士学位论文全文数据库 工程科技I辑》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111024433A (en) * | 2019-12-30 | 2020-04-17 | 辽宁大学 | Industrial equipment health state detection method for optimizing support vector machine by improving wolf algorithm |
| CN111242005A (en) * | 2020-01-10 | 2020-06-05 | 西华大学 | Heart sound classification method based on improved wolf colony algorithm optimization support vector machine |
| CN111242005B (en) * | 2020-01-10 | 2023-05-23 | 西华大学 | Heart sound classification method based on improved wolf's swarm optimization support vector machine |
| CN111368892A (en) * | 2020-02-27 | 2020-07-03 | 合肥工业大学 | Generalized S transformation and SVM electric energy quality disturbance efficient identification method |
| CN111368892B (en) * | 2020-02-27 | 2024-01-30 | 合肥工业大学 | Electric energy quality disturbance efficient identification method for generalized S transformation and SVM |
| CN111428418A (en) * | 2020-02-28 | 2020-07-17 | 贵州大学 | Bearing fault diagnosis method and device, computer equipment and storage medium |
| CN111272429B (en) * | 2020-03-04 | 2021-08-17 | 贵州大学 | Bearing fault diagnosis method |
| CN111272429A (en) * | 2020-03-04 | 2020-06-12 | 贵州大学 | Bearing fault diagnosis method |
| CN111563348A (en) * | 2020-04-10 | 2020-08-21 | 西安工程大学 | Transformer fault diagnosis method based on deep support vector machine |
| CN111563348B (en) * | 2020-04-10 | 2023-04-18 | 西安工程大学 | Transformer fault diagnosis method based on deep support vector machine |
| CN111603161A (en) * | 2020-05-28 | 2020-09-01 | 苏州小蓝医疗科技有限公司 | Electroencephalogram classification method |
| CN112052934B (en) * | 2020-09-08 | 2024-03-01 | 江南大学 | Motor bearing fault diagnosis method based on improved gray wolf optimization algorithm |
| CN112052934A (en) * | 2020-09-08 | 2020-12-08 | 江南大学 | Motor bearing fault diagnosis method based on improved wolf optimization algorithm |
| CN112285541A (en) * | 2020-09-21 | 2021-01-29 | 南京理工大学 | Fault diagnosis method for current frequency conversion circuit |
| CN112288001A (en) * | 2020-10-28 | 2021-01-29 | 北京航空航天大学 | GWO oversampling-based high-speed rail brake system fault detection SVM method |
| CN112288001B (en) * | 2020-10-28 | 2021-11-23 | 北京航空航天大学 | GWO oversampling-based high-speed rail brake system fault detection SVM method |
| CN112836604A (en) * | 2021-01-22 | 2021-05-25 | 合肥工业大学 | Rolling bearing fault diagnosis and classification method, system and equipment based on VMD-SSAE and storage medium thereof |
| CN113670609A (en) * | 2021-07-21 | 2021-11-19 | 广州大学 | Fault detection method, system, device and medium based on wolf optimization algorithm |
| CN113917287A (en) * | 2021-11-22 | 2022-01-11 | 国家电网有限公司 | Substation bus joint discharge heating fault monitoring system |
| CN113923104A (en) * | 2021-12-07 | 2022-01-11 | 南京信息工程大学 | Network fault diagnosis method, equipment and storage medium based on wavelet neural network |
| CN114781577A (en) * | 2022-05-06 | 2022-07-22 | 安徽理工大学 | Buck circuit fault diagnosis method based on VMD-DCNN-SVM |
| CN115032270A (en) * | 2022-06-01 | 2022-09-09 | 北京科技大学 | Method and device for quantitatively identifying damage state of building curtain wall based on machine learning algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110132596A (en) | A method of the rolling bearing fault diagnosis based on wavelet packet and GWO-SVM | |
| CN107727395B (en) | A kind of Method for Bearing Fault Diagnosis based on full variation and uncompensation distance assessment | |
| CN107631867B (en) | A kind of rotating machinery fault intelligent method for classifying based on deep learning | |
| Samanta et al. | Artificial neural networks and genetic algorithm for bearing fault detection | |
| CN107677472B (en) | The bearing state noise diagnostics algorithm that network-oriented Variable Selection is merged with Characteristic Entropy | |
| CN110567720A (en) | method for diagnosing depth confrontation of fault of fan bearing under unbalanced small sample scene | |
| CN105243388B (en) | Waveform classification based on dynamic time warping and partitioning algorithm | |
| CN109186964A (en) | Rotary machinery fault diagnosis method based on angle resampling and ROC-SVM | |
| CN110018322B (en) | Rotating speed detection method and system based on deep learning | |
| CN111695598A (en) | Monitoring data abnormity diagnosis method based on generation countermeasure network | |
| CN111174370A (en) | Fault detection method and device, storage medium and electronic device | |
| CN112819059A (en) | Rolling bearing fault diagnosis method based on popular retention transfer learning | |
| CN109374293B (en) | Gear fault diagnosis method | |
| CN113340598B (en) | Rolling bearing intelligent fault diagnosis method based on regularized sparse model | |
| CN112364706A (en) | Small sample bearing fault diagnosis method based on class imbalance | |
| CN114112398A (en) | Fault diagnosis method for rolling bearing under variable speed working condition | |
| CN117668488A (en) | Cross-working-condition reinforcement learning fault diagnosis method | |
| CN114462480A (en) | Multi-source sensor rolling mill fault diagnosis method based on non-equilibrium data set | |
| Netzer et al. | Intelligent anomaly detection of machine tools based on mean shift clustering | |
| CN116401603A (en) | Multi-mode bearing fault intelligent diagnosis method based on transfer learning | |
| CN116011507A (en) | Rare fault diagnosis method for fusion element learning and graph neural network | |
| Jiang et al. | A novel antibody population optimization based artificial immune system for rotating equipment anomaly detection | |
| CN113837071B (en) | Partial migration fault diagnosis method based on multiscale weight selection countermeasure network | |
| CN111476363A (en) | Stable learning method and device for distinguishing decorrelation of variables | |
| CN116644304A (en) | Similarity-based truck bearing abnormal feature extraction and classification 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190816 |