CN108362488A - OLTC mechanical failure diagnostic methods based on MPE and SVM - Google Patents
OLTC mechanical failure diagnostic methods based on MPE and SVM Download PDFInfo
- Publication number
- CN108362488A CN108362488A CN201810166483.0A CN201810166483A CN108362488A CN 108362488 A CN108362488 A CN 108362488A CN 201810166483 A CN201810166483 A CN 201810166483A CN 108362488 A CN108362488 A CN 108362488A
- Authority
- CN
- China
- Prior art keywords
- svm
- oltc
- time series
- mpe
- data point
- 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
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a kind of OLTC mechanical failure diagnostic methods based on MPE and SVM, include the following steps：1）The vibration signal under load ratio bridging switch OLTC normal conditions, the vibration signal under malfunction are acquired, and are pre-processed to vibration signal by acceleration transducer；2）Multiple dimensioned arrangement entropy MPE is carried out to collected vibration signal to calculate, construction feature vector, the input as support vector machines；3）By step 2）Obtained feature vector is input in support vector machines, is trained to support vector machines, and test data is input to trained SVM, to judge that the fault mode of OLTC, the present invention do not need the training that mass data carries out SVM, diagnostic accuracy higher；BP neural network is substantially better than to the diagnosis effect of OLTC.
Description
Technical field
The present invention relates to load ratio bridging switch fault diagnosis technology fields, and in particular to a kind of to have load based on MPE and SVM
Tap switch OLTC mechanical failure diagnostic methods.
Background technology
With the raising required power quality, power grid widely applies the systems such as automatism voltage control, existing loaded tap-off
Switch (OLTC) adjusting is quite frequent, and rate of breakdown is very high.It is counted according to data at home and abroad, tap switch failure accounts for transformer event
20% or more of barrier, and predominantly mechanical breakdown, if finding and handling not in time, failure can seriously destroy OLTC and transformer
Inherent structure, influence the normal safe operation of power equipment and system and cause serious consequence.Therefore, in order to ensure tap is opened
Pass is safely and reliably run, it is necessary to carry out the correlative study of tap switch mechanical failure diagnostic method.
In load ratio bridging switch operating process, collision or friction between mechanism parts will produce vibration signal, this
Vibration signals include abundant status information of equipment a bit.Currently, having become load ratio bridging switch machine based on analysis of vibration signal
The important means of tool fault diagnosis.Existing analysis of vibration signal method has Wavelet Singularity detection, self-organizing map, EMD
(empirical mode decomposition) and wavelet packet etc..These methods are that non-stationary signal is decomposed into several simple stationary signals mostly
The sum of, then each component is handled, extracts time-frequency characteristics.However, studies have shown that the vibration in OLTC handoff procedures is believed
Number apparent non-linear behavior is shown, using the method for time frequency analysis, is stationary signal by signal decomposition, inevitably has certain
Limitation.Therefore, the present invention carries out OLTC mechanical fault diagnosis, Neng Gouzhi using multiple dimensioned arrangement entropy nonlinear analysis method
Connect the fault message that other methods can not extract in extraction mechanical oscillation signal.
For the non-linear behavior of OLTC mechanical oscillation signals, time series randomness of the present invention from OLTC vibration signals
It sets out with dynamics catastrophe characteristics, the extraction of the fault signature by multiple dimensioned arrangement entropy (MPE) applied to OLTC.Due to support to
Amount machine (SVM) analysis has good diagnosis effect in Small Sample Database fault diagnosis, therefore, fault signature is extracted in MPE
On the basis of, judge as fault type in conjunction with SVM, proposes that a kind of load ratio bridging switch mechanical breakdown based on MPE and SVM is examined
Disconnected method, and it is applied to the analysis of OLTC experimental datas.The result shows that the method can effectively diagnose OLTC machinery events
Hinder type.
Invention content
To solve deficiency in the prior art, the present invention provides a kind of load ratio bridging switch machinery event based on MPE and SVM
Hinder diagnostic method, the certain precision of diagnostic result is high, and simple in structure, operability is strong.
In order to realize that above-mentioned target, the present invention adopt the following technical scheme that：A kind of OLTC machinery events based on MPE and SVM
Hinder diagnostic method, it is characterised in that：Include the following steps：
1) by acceleration transducer under load ratio bridging switch OLTC normal conditions vibration signal, under malfunction
Vibration signal is acquired, and is pre-processed to vibration signal；
2) it carries out multiple dimensioned arrangement entropy MPE to collected vibration signal to calculate, construction feature vector, as supporting vector
The input of machine SVM；
3) feature vector that step 2) obtains is input in support vector machines, support vector machines is instructed
Practice, test data is input to trained SVM, to judge the fault mode of OLTC.
A kind of OLTC mechanical failure diagnostic methods based on MPE and SVM above-mentioned, it is characterized in that：The pretreatment is specific
For：Noise reduction process is carried out to collected vibration signal.
A kind of OLTC mechanical failure diagnostic methods based on MPE and SVM above-mentioned, it is characterized in that：The malfunction packet
It includes load ratio bridging switch OLTC contact slaps and spring performance declines.
A kind of OLTC mechanical failure diagnostic methods based on MPE and SVM above-mentioned, it is characterized in that：The acceleration sensing
Device is mounted on the top of tap switch.
A kind of OLTC mechanical failure diagnostic methods based on MPE and SVM above-mentioned, it is characterized in that：The multiple dimensioned arrangement
Entropy MPE calculate the specific steps are：
1) to original time series { x1,x2,…,xNCoarse processing is carried out, multiple dimensioned time sequence is constructed according to the following formula
Arrange { yl (s)}：
In formula, s is scale factor, and N is the length of original time series, xiIndicate the data point in original time series, i
Ranging from 1-N, yl (s)Indicate first of average value of time series under s windows；
2) after to the processing of original time series coarse, the arrangement entropy after each coarseness time series normalization is calculated,
Multiple dimensioned arrangement entropy, constitutive characteristic amount are obtained.
A kind of OLTC mechanical failure diagnostic methods based on MPE and SVM above-mentioned, it is characterized in that：After the normalization
Arrangement entropy specifically calculates step and is：
Assuming that one group of time series { xi| i=1,2 ..., N }, phase space reconfiguration is carried out to it, the time sequence reconstructed
Arrange Xi：
Xi=[xi,xi+τ,…,xi+(m-1)τ] (1)
Wherein, m is Embedded dimensions, and τ is delay time, xiFor time series XiIn i-th of data point, xi+τFor time series
XiIn the i-th+τ data points, xi+(m-1)τFor time series XiIn i-th+(m-1) τ data point, by time series XiIn m number
Strong point is arranged by ascending order, i.e.,R indicates reproducing sequence XiThe position of middle data point,Attach most importance to
Structure sequence XiMiddle data point is by the 2nd data point after ascending order arrangement, similarlyTo reconstruct sequence XiMiddle data point is arranged by ascending order
M-th strong point afterwards；Work as presenceWhen, data pointBy rj、rkSize arranged, even rj<rk, then
ThinkIndicate reproducing sequence XiIn rjA data point, rj、rkIndicate reproducing sequence XiWhere middle data point
Position,Indicate reproducing sequence XiIn rkA data point；
Time series XiThere is m！Middle arrangement mode, to any arrangement mode ω, T (ω) indicates its number occurred, then
Its occur probability be：
Therefore, time series XiArrangement entropy HPEIt may be defined as：
HPE=-∑ P (ω) lnP (ω) (3)
Arrangement entropy PE after being normalized after normalization：
A kind of OLTC mechanical failure diagnostic methods based on MPE and SVM above-mentioned, it is characterized in that：The vibration data point
At two groups, every group includes normal vibration signal and fault-signal, one group of training for being used for SVM, another group of test for being used for SVM；
In step 3), the training feature vector after normalization is first input to support by feature vector normalized between [0,1]
In vector machine SVM, support vector machines is trained, is then input to the testing feature vector after normalization trained
SVM, to judge the fault mode of OLTC.
The advantageous effect that the present invention is reached：
1, the present invention carries out OLTC mechanical fault diagnosis using multiple dimensioned arrangement entropy nonlinear analysis method, can be direct
The fault message that other methods can not extract in extraction mechanical oscillation signal, such as the randomness of fault message；
2, the present invention does not need the training that mass data carries out SVM, diagnostic accuracy higher；
3, the present invention is substantially better than BP neural network to the diagnosis effect of OLTC.
Description of the drawings
Fig. 1 is the characteristic extraction procedure figure based on multiple dimensioned arrangement entropy；
Fig. 2 is the multiple dimensioned arrangement entropy MPE distribution maps under three kinds of states.
Specific implementation mode
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating the present invention
Technical solution, and not intended to limit the protection scope of the present invention.
A kind of load ratio bridging switch OLTC mechanical failure diagnostic methods based on MPE and SVM, include the following steps：
1) by acceleration transducer under load ratio bridging switch OLTC normal conditions vibration signal, under malfunction
Vibration signal is acquired, and is pre-processed to vibration signal, i.e., carries out noise reduction process to collected vibration signal；
2) it carries out multiple dimensioned arrangement entropy MPE to collected vibration signal to analyze, construction feature vector, as supporting vector
The input of machine SVM；
3) feature vector that step 2) constructs is input in support vector machines, support vector machines is instructed
Practice, test data is input to trained SVM, to judge the fault mode of OLTC.
Acceleration transducer is adsorbed on the peace on the surface of load ratio bridging switch OLTC test points using permanent magnet in step 1)
Dress mode, this mounting means is simple and practicable, is suitble to frequently replace the occasion of test point.In view of the propagation medium of vibration signal
And vibrating sensor is mounted on the top of tap switch, the vibration that this position is picked up by the damping of communication process, the present invention
Signal high frequency attenuation is fewer, and signal is more complete；Collected vibration data is divided into two groups, every group all includes that normal vibration is believed
Number and fault-signal, one group be used for SVM training, another group be used for SVM test.
Malfunction in step 1) refers to that load ratio bridging switch OLTC contact slaps and spring performance decline two kinds of feelings
Condition；
Vibration signal is pre-processed in step 1), noise reduction process specially has been carried out to vibration signal.
In step 2), multiple dimensioned arrangement entropy is carried out to collected vibration signal and is analyzed, construction feature vector.Multiple dimensioned row
Row entropy is the arrangement entropy that time series is calculated on multiple scales.
Arrangement entropy specific algorithm be：
Assuming that one group of time series { xi| i=1,2 ..., N }, phase space reconfiguration is carried out to it, the time sequence reconstructed
Arrange Xi：
Xi=[xi,xi+τ,…,xi+(m-1)τ] (1)
Wherein, m is Embedded dimensions, and τ is delay time, and N is the length of time series, xiFor time series XiIn i-th number
Strong point, xi+τFor time series XiIn the i-th+τ number, xi+(m-1)τFor time series XiIn i-th+(m-1) τ number, by time series
XiIn m data press ascending order arrangement, i.e.,R indicates reproducing sequence XiMiddle data point
Position,To reconstruct sequence XiMiddle data point is by the 2nd number after ascending order arrangement, similarlyTo reconstruct sequence XiMiddle data point
M-th strong point after being arranged by ascending order；Work as presenceWhen, data pointBy rj、rkSize arranged,
Even rj<rk, then it is assumed thatIndicate reproducing sequence XiIn rjA data point, rj、rkIndicate reproducing sequence Xi
Middle data point position,Indicate reproducing sequence XiIn rkA data point.
Random time sequence XiThere is m！Middle arrangement mode, to any arrangement mode ω, T (ω) indicates its time occurred
It counts, then its probability occurred is：
Therefore, time series XiArrangement entropy HPEIt may be defined as：
HPE=-∑ P (ω) lnP (ω) (3)
Arrangement entropy PE after being normalized after normalization：
The size of PE values reflects the complexity and randomness of time series signal, and value is bigger, illustrates that time series is believed
It is number more complicated, conversely, then more regular.Therefore, the transformation of PE values reflects and is exaggerated the subtle transformation in part of time series.
As shown in Figure 1, multiple dimensioned arrangement entropy (MPE) analysis method the specific steps are：
1) to original time series { x1,x2,…,xNCoarse processing is carried out, multiple dimensioned time sequence is constructed according to the following formula
Arrange { yl (s)}：
In formula, s is scale factor, and N is the length of original time series, xiIndicate the data point in original time series, yl (s)Indicate first of average value of time series under s windows.
2) it after to the processing of original time series coarse, calculates each coarseness time series according to formula (1)-(4) and returns
One change after arrangement entropy to get to multiple dimensioned arrangement entropy, as feature vector.
In step 3), first use data processing-normalized function mapminmax that matlab is carried by feature vector normalizing
Change processing between [0,1], the training feature vector after normalization is input in SVM, SVM is trained, then will be returned
Testing feature vector after one change is input to trained SVM, to judge the fault mode of OLTC.
Embodiment：
To CMIII-500-63B-10193W type tap switch simulated experiments.This tap switch is three-phase Y connections, maximum
Tap position number is 19.Vibrating sensor is using the LC0151 type piezoelectric type accelerations of high resolution and strong antijamming capability sensing
Device.The present invention is mounted on vibrating sensor on the top of tap switch, and the vibration signal high frequency attenuation that this position is picked up compares
Few, signal is more complete.By acceleration transducer to the vibration signal under OLTC normal conditions, malfunction (OLTC contact pines
Dynamic and spring performance declines) under vibration signal be acquired, collected vibration data is divided into 2 groups, every group all includes
Normal vibration signal and fault-signal, one group of training for being used for SVM, another group of test for being used for SVM；
MPE analyses are carried out to collected vibration signal, construction feature vector as the input of SVM, instructs SVM
Practice, test data is input to trained SVM, to judge the fault mode of OLTC.
First use the mapminmax that matlab is carried by between characteristic quantity normalized [0,1], by the instruction after normalization
Practice characteristic quantity to be input in SVM, SVM is trained, is then input to the test feature amount after normalization trained
SVM, to judge the fault mode of OLTC.
It is multiple dimensioned arrangement entropy influence factor be：When carrying out feature extraction using multiple dimensioned arrangement entropy, Embedded dimensions m, prolong
Slow time τ and scale factor s will have a direct impact on result of calculation：If m is too small, the quantity of state for including in the vector of reconstruct is few, calculates
Method loses meaning, if m values are excessive, the reconstruct of phase space will homogenization time sequence, it is long not only to calculate the time at this time, and
And it can not also reflect that the subtle transformation of sequence, Bandt suggest that Embedded dimensions m takes 3~7, and the present embodiment takes 7；Delay time T pair
The calculating of sequence influences smaller, the present embodiment selection τ=1；And scale factor s>When 10, the dynamics under system different scale becomes
Law can just show, and the present embodiment s takes 12.
If Fig. 2 is the multiple dimensioned arrangement entropy under three kinds of states, as shown in Figure 2, tap switch is under normal condition to return
Arrangement entropy PE after one change is apparently higher than malfunction, and it is 8 that contact slap and spring performance, which decline both mechanical breakdowns in s,
Later its PE differences are smaller, thus illustrate, it for s maximum values is suitable to take 12, is fully demonstrated by the dynamic law of signal.This
Outside, when mechanical breakdown occurs for OLTC, the randomness of vibration signal is smaller, and complexity is lower, and the PE of vibration signal is smaller at this time；
Conversely, when OLTC is in normal condition, the randomness of vibration signal is maximum, and PE values are also maximum.Thus illustrate the variation of PE values
It can reflect OLTC mechanical breakdown degree well.
SVM based on MPE characteristic quantities compares the diagnosis effect of OLTC with BP neural network, obtains shown in table 1
Prediction comparison result：
1 present invention of table is compared with BP neural network prediction result
Note：1 expression tap switch is in normal condition, and 2 expression tap switches are in contact slap failure, and 3 indicate tap
Switch declines failure in spring performance.
BP neural network is trained using same 15 groups of data, and this 15 groups of data are predicted, by table
As can be seen that the OLTC mechanical failure diagnostic methods based on MPE and SVM can efficiently identify the type that is out of order, to illustrate
The feasibility of the present invention, is also known by table 1, and diagnosis effect of the present invention is better than BP neural network.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (7)
1. a kind of OLTC mechanical failure diagnostic methods based on MPE and SVM, it is characterised in that：Include the following steps：
1) by acceleration transducer to the vibration signal under load ratio bridging switch OLTC normal conditions, the vibration under malfunction
Signal is acquired, and is pre-processed to vibration signal；
2) it carries out multiple dimensioned arrangement entropy MPE to collected vibration signal to calculate, construction feature vector, as support vector machines
The input of SVM；
3) feature vector that step 2) obtains is input in support vector machines, support vector machines is trained, it will
Test data is input to trained SVM, to judge the fault mode of OLTC.
2. a kind of OLTC mechanical failure diagnostic methods based on MPE and SVM according to claim 1, it is characterized in that：It is described
Pretreatment is specially：Noise reduction process is carried out to collected vibration signal.
3. a kind of OLTC mechanical failure diagnostic methods based on MPE and SVM according to claim 1, it is characterized in that：It is described
Malfunction includes that load ratio bridging switch OLTC contact slaps and spring performance decline.
4. a kind of OLTC mechanical failure diagnostic methods based on MPE and SVM according to claim 1, it is characterized in that：It is described
Acceleration transducer is mounted on the top of tap switch.
5. a kind of OLTC mechanical failure diagnostic methods based on MPE and SVM according to claim 1, it is characterized in that：It is described
Multiple dimensioned arrangement entropy MPE calculate the specific steps are：
1) to original time series { x1,x2,…,xNCoarse processing is carried out, multiple dimensioned time series { y is constructed according to the following formulal (s)}：
In formula, s is scale factor, and N is the length of original time series, xiIndicate the data point in original time series, the model of i
It encloses for 1-N, yl (s)Indicate first of average value of time series under s windows；
2) after to the processing of original time series coarse, calculate the arrangement entropy after the normalization of each coarseness time series to get
Multiple dimensioned arrangement entropy, constitutive characteristic amount are arrived.
6. a kind of OLTC mechanical failure diagnostic methods based on MPE and SVM according to claim 5, it is characterized in that：It is described
Arrangement entropy after normalization specifically calculates step：
Assuming that one group of time series { xi| i=1,2 ..., N }, phase space reconfiguration is carried out to it, the time series X reconstructedi：
Xi=[xi,xi+τ,…,xi+(m-1)τ] (1)
Wherein, m is Embedded dimensions, and τ is delay time, xiFor time series XiIn i-th of data point, xi+τFor time series XiIn
I-th+τ data points, xi+(m-1)τFor time series XiIn i-th+(m-1) τ data point, by time series XiIn m data
Ascending order arrangement is pressed, i.e.,R indicates reproducing sequence XiThe position of middle data point,For reconstruct
Sequence XiMiddle data point is by the 2nd data point after ascending order arrangement, similarlyTo reconstruct sequence XiMiddle data point is arranged by ascending order
M-th strong point afterwards；Work as presenceWhen, data pointBy rj、rkSize arranged, even rj<rk, then
Think Indicate reproducing sequence XiIn rjA data point, rj、rkIndicate reproducing sequence XiMiddle data point institute is in place
It sets,Indicate reproducing sequence XiIn rkA data point；
Time series XiThere is m！Middle arrangement mode, to any arrangement mode ω, T (ω) indicates its number occurred, then it occurs
Probability be：
Therefore, time series XiArrangement entropy HPEIt may be defined as：
HPE=-∑ P (ω) ln P (ω) (3)
Arrangement entropy PE after being normalized after normalization：
7. a kind of OLTC mechanical failure diagnostic methods based on MPE and SVM according to claim 1, it is characterized in that：It is described
Vibration data is divided into two groups, and every group includes normal vibration signal and fault-signal, and one group of training for being used for SVM, another group is used for
The test of SVM；In step 3), first by feature vector normalized between [0,1], by the training feature vector after normalization
It is input in support vector machines, support vector machines is trained, be then input to the testing feature vector after normalization
Trained SVM, to judge the fault mode of OLTC.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810166483.0A CN108362488A (en) | 2018-02-28 | 2018-02-28 | OLTC mechanical failure diagnostic methods based on MPE and SVM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810166483.0A CN108362488A (en) | 2018-02-28 | 2018-02-28 | OLTC mechanical failure diagnostic methods based on MPE and SVM |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108362488A true CN108362488A (en) | 2018-08-03 |
Family
ID=63003316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810166483.0A Pending CN108362488A (en) | 2018-02-28 | 2018-02-28 | OLTC mechanical failure diagnostic methods based on MPE and SVM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108362488A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109117450A (en) * | 2018-08-04 | 2019-01-01 | 华北水利水电大学 | The determination method for measured data optimized analysis length of shaking |
| CN109813420A (en) * | 2019-01-18 | 2019-05-28 | 国网江苏省电力有限公司检修分公司 | A kind of shunt reactor method for diagnosing faults based on Fuzzy-ART |
| CN109856530A (en) * | 2018-12-25 | 2019-06-07 | 国网江苏省电力有限公司南京供电分公司 | A kind of load ratio bridging switch on-line monitoring method for diagnosing faults |
| CN110132567A (en) * | 2019-05-28 | 2019-08-16 | 河海大学 | A kind of OLTC method for diagnosing faults based on LCD and arrangement entropy |
| CN110146268A (en) * | 2019-05-28 | 2019-08-20 | 河海大学 | A kind of OLTC method for diagnosing faults based on mean value decomposition algorithm |
| CN110378065A (en) * | 2019-07-29 | 2019-10-25 | 河海大学 | A kind of large deformation plate non-linear vibratory signal State Space Reconstruction based on normal parameter |
| CN112014047A (en) * | 2020-08-27 | 2020-12-01 | 华侨大学 | Mechanical fault diagnosis method for on-load tap-changer |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104849050A (en) * | 2015-06-02 | 2015-08-19 | 安徽工业大学 | Rolling bearing fault diagnosis method based on composite multi-scale permutation entropies |
| CN105758644A (en) * | 2016-05-16 | 2016-07-13 | 上海电力学院 | Rolling bearing fault diagnosis method based on variation mode decomposition and permutation entropy |
| CN105956526A (en) * | 2016-04-22 | 2016-09-21 | 山东科技大学 | Method for identifying a microearthquake event with low signal-to-noise ratio based on multi-scale permutation entropy |
| CN106644484A (en) * | 2016-09-14 | 2017-05-10 | 西安工业大学 | Turboprop Engine rotor system fault diagnosis method through combination of EEMD and neighborhood rough set |
| CN105354587B (en) * | 2015-09-25 | 2017-09-05 | 国网甘肃省电力公司电力科学研究院 | A kind of method for diagnosing faults of wind-driven generator group wheel box |
-
2018
- 2018-02-28 CN CN201810166483.0A patent/CN108362488A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104849050A (en) * | 2015-06-02 | 2015-08-19 | 安徽工业大学 | Rolling bearing fault diagnosis method based on composite multi-scale permutation entropies |
| CN105354587B (en) * | 2015-09-25 | 2017-09-05 | 国网甘肃省电力公司电力科学研究院 | A kind of method for diagnosing faults of wind-driven generator group wheel box |
| CN105956526A (en) * | 2016-04-22 | 2016-09-21 | 山东科技大学 | Method for identifying a microearthquake event with low signal-to-noise ratio based on multi-scale permutation entropy |
| CN105758644A (en) * | 2016-05-16 | 2016-07-13 | 上海电力学院 | Rolling bearing fault diagnosis method based on variation mode decomposition and permutation entropy |
| CN106644484A (en) * | 2016-09-14 | 2017-05-10 | 西安工业大学 | Turboprop Engine rotor system fault diagnosis method through combination of EEMD and neighborhood rough set |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109117450A (en) * | 2018-08-04 | 2019-01-01 | 华北水利水电大学 | The determination method for measured data optimized analysis length of shaking |
| CN109856530A (en) * | 2018-12-25 | 2019-06-07 | 国网江苏省电力有限公司南京供电分公司 | A kind of load ratio bridging switch on-line monitoring method for diagnosing faults |
| CN109856530B (en) * | 2018-12-25 | 2021-11-02 | 国网江苏省电力有限公司南京供电分公司 | On-load tap-changer on-line monitoring fault diagnosis method |
| CN109813420A (en) * | 2019-01-18 | 2019-05-28 | 国网江苏省电力有限公司检修分公司 | A kind of shunt reactor method for diagnosing faults based on Fuzzy-ART |
| CN110132567A (en) * | 2019-05-28 | 2019-08-16 | 河海大学 | A kind of OLTC method for diagnosing faults based on LCD and arrangement entropy |
| CN110146268A (en) * | 2019-05-28 | 2019-08-20 | 河海大学 | A kind of OLTC method for diagnosing faults based on mean value decomposition algorithm |
| CN110378065A (en) * | 2019-07-29 | 2019-10-25 | 河海大学 | A kind of large deformation plate non-linear vibratory signal State Space Reconstruction based on normal parameter |
| CN112014047A (en) * | 2020-08-27 | 2020-12-01 | 华侨大学 | Mechanical fault diagnosis method for on-load tap-changer |
| CN112014047B (en) * | 2020-08-27 | 2022-05-03 | 华侨大学 | Mechanical fault diagnosis method for on-load tap-changer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108362488A (en) | OLTC mechanical failure diagnostic methods based on MPE and SVM | |
| US20210167584A1 (en) | Gis mechanical fault diagnosis method and device | |
| Yang et al. | Condition evaluation for opening damper of spring operated high-voltage circuit breaker using vibration time-frequency image | |
| CN105528741B (en) | Circuit breaker state identification method based on multi-signal feature fusion | |
| CN108398252A (en) | OLTC mechanical failure diagnostic methods based on ITD and SVM | |
| Huang et al. | An intelligent fault diagnosis method of high voltage circuit breaker based on improved EMD energy entropy and multi-class support vector machine | |
| CN110926778B (en) | Mechanical fault diagnosis method for gas insulated switchgear assembly based on abnormal vibration | |
| Hong et al. | A variational mode decomposition approach for degradation assessment of power transformer windings | |
| Dao et al. | Lamb wave based structural damage detection using cointegration and fractal signal processing | |
| CN110146268A (en) | A kind of OLTC method for diagnosing faults based on mean value decomposition algorithm | |
| CN110146269A (en) | The OLTC method for diagnosing faults of multiple dimensioned fuzzy entropy based on EEMD | |
| CN103823180A (en) | Method for diagnosing mechanical faults of distribution switch | |
| CN106932184A (en) | A kind of Diagnosis Method of Transformer Faults based on improvement hierarchical clustering | |
| Ma et al. | GIS mechanical state identification and defect diagnosis technology based on self‐excited vibration of assembled circuit breaker | |
| Yang et al. | Fault diagnosis of circuit breakers based on time–frequency and chaotic vibration analysis | |
| CN1232834C (en) | Online detection method for vacuum circuit breaker contact on-off time based on vibration analysis | |
| CN113297922B (en) | High-voltage switch cabinet fault diagnosis method, device and storage medium | |
| CN111678699A (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| CN117390408B (en) | Power transformer operation fault detection method and system | |
| CN109632291A (en) | A kind of Fault Diagnosis of Gear Case method based on polynary mode decomposition-transfer entropy | |
| CN113551895A (en) | Comprehensive intelligent diagnosis method for mechanical fault of on-load tap-changer | |
| CN105241643A (en) | High-voltage circuit breaker mechanical state monitoring method employing HS transformation and single-type support vector machine | |
| Peng et al. | Simulation test study on fatigue characteristics of circuit breaker insulation pull rod | |
| Shuyou et al. | Extracting power transformer vibration features by a time-scale-frequency analysis method | |
| CN109946597A (en) | Tap switch operating status appraisal procedure based on dynamoelectric signal |
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: 20180803 |