CN109375041A - Single-phase grounded malfunction in grounded system of low current judgment method - Google Patents
Single-phase grounded malfunction in grounded system of low current judgment method Download PDFInfo
- Publication number
- CN109375041A CN109375041A CN201811582682.6A CN201811582682A CN109375041A CN 109375041 A CN109375041 A CN 109375041A CN 201811582682 A CN201811582682 A CN 201811582682A CN 109375041 A CN109375041 A CN 109375041A
- Authority
- CN
- China
- Prior art keywords
- value
- phase
- fault
- grounded
- vector
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/085—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution lines, e.g. overhead
Abstract
The present invention relates to a kind of single-phase grounded malfunction in grounded system of low current judgment methods to identify singlephase earth fault.The singlephase earth fault that the present invention constructs judges in Fisher classifier, combines the ground fault feature vector signal of transient characteristic and steady state characteristic.Angle research is shifted from state, when line single phase grounding failure occurs in small current neutral grounding system, route electric field and curent change are the process changed again to stable state from stable state to temporal variations in fact.So the present invention can more simulate actual conditions when singlephase earth fault occurs, judgement fast and accurately can be distinguished to single-phase grounded malfunction in grounded system of low current using the Fisher classifier that this method constructs.
Description
Technical field
The present invention relates to a kind of single-phase grounded malfunction in grounded system of low current judgment methods.
Background technique
The judgement of 10KV overhead transmission line singlephase earth fault is always one of the problem in power distribution network industry.It is a large amount of in recent years exhausted
Edge conducting wire comes into operation in overhead transmission line, further increases the identification difficulty of broken string singlephase earth fault.Although at present
It is proposed that the methods of injecting signal, transient state analysis method, first half-wave method, colony amplitude comparison phase comparing method, zero sequence power method go to solve
Single-phase earth fault line selection and orientation problem.But since distribution net work structure is more complicated, neutral grounding mode is different, single-phase connects
Ground transition resistance resistance value is indefinite and grounding point is from factors such as electric substation's exit distance differences causes ground signalling feature at certain
It is not significant enough in a little situations, it is difficult to effectively to extract.Field practice shows that existing method also needs to further increase alarm accurately
Rate.
In fact, the medium voltage distribution network fault location system based on fault detector promoted the use of in current national grid
In, singlephase earth fault solution can be probably divided into and outer apply signalling and non-outer apply two class of signalling.The former alarms standard
Can true property and Injection Signal frequency have much relations, form signal circuit and detection device using signal is applied outside being above limited to
Signal characteristic is applied outside being correctly detecting.Non- outer signalling of applying can be easy to constitute distribution with very big Installation Flexibility
Network parameters distributed monitoring system.This method can refine again is divided into two class of transient characteristic method and steady state characteristic method.Further
The non-outer various methods applied in signalling are studied, often the transient characteristic of accentuator circuit parameter or stable state are special for discovery existing method
The ground connection feature signal extraction of the single aspect of sign lacks the building in a kind of method and combines connecing for transient characteristic and steady state characteristic
Earth fault feature vector signal.Thus only it can not solve the problems, such as that singlephase earth fault identifies very well with transient method or steady state method.
Therefore need to establish the theoretical model for combining transient state and steady-state signal feature, preferably to identify singlephase earth fault.
Summary of the invention
It is an object of the invention to establish the small current neutral grounding system of a kind of combination transient signal feature and steady-state signal feature
Singlephase earth fault judgment method of uniting is to identify singlephase earth fault.
To achieve the above object, single-phase grounded malfunction in grounded system of low current judgment method of the invention uses following technology
Scheme:
Single-phase grounded malfunction in grounded system of low current judgment method, comprising the following steps: the first step extracts single-phase transient state electricity
Flow characteristic component Wvalue, wherein WvalueFor the 3rd layer of small echo mode coefficient maximum value of line current db5 wavelet transformation, line current
The 3rd layer of small echo mode coefficient of db5 wavelet transformationC in formula3[k]=2-3/2F [k],
Wherein h0[k] is wavelet decomposition filter, and j and k respectively represent scale label and translation label；
Second step establishes singlephase earth fault and judges Fisher classifier, the classification in Fisher classifier established
Discriminant function is y=c1x1+c2x2+c3x3+…+cpxp, by x in formula1、x2、x3、…、xpThe matrix X of compositioniFor specific low current
The row vector acquired in earthed system, wherein by c1、c2、c3、…、cpThe Matrix C of compositioniAccording toIt is determined when taking maximum；
Third step constructs single-phase statistical vector ξ=(W of small current neutral grounding systemvalue, I, E), and according to the statistics of construction
Vector determines in discriminant classification function by c1、c2、c3The Matrix C of compositioniSpecific value, wherein I be line fault before and failure
Current effective value afterwards, E are represented before line fault and after failure to earth electric field virtual value；
4th step calculates feature vector y and critical vector y0And judge whether that ground fault occurs, wherein y is according to third
The determining discriminant classification function of step is calculated, according toDetermine critical value y0, whereinBefore line fault
The average value of all feature vector y,For the average value of feature vector y all under line fault conditions；If y < y0, then occur
Singlephase earth fault；If y >=y0, then new feature vector belongs to ungrounded fault condition.
In the single-phase statistical vector ξ constructed in the third step, it is added Total 4 groups of pre-established ground fault data are adaptive to establish the Fisher
Classifier, (n in formula1%, n2%) fall range for the alarm of line electricity field measure ground fault.
Beneficial effects of the present invention are as follows: the singlephase earth fault that the present invention constructs judges in Fisher classifier, in conjunction with
The ground fault feature vector signal of transient characteristic and steady state characteristic.Angle research is shifted from state, when low current connects
When line single phase grounding failure occurs in ground system, route electric field and curent change be in fact one from stable state to temporal variations again
The process changed to stable state.So the present invention can more simulate actual conditions when singlephase earth fault occurs, this method structure is used
The Fisher classifier built fast and accurately can distinguish judgement to single-phase grounded malfunction in grounded system of low current.
Further, by introducing 4 groups of pre-established ground fault data, so that Fisher classifier established by the present invention
With adaptive learning ability.
Detailed description of the invention
Fig. 1 is is judged using the embodiment one of single-phase grounded malfunction in grounded system of low current judgment method of the invention
Route electric field curve diagram.
Specific embodiment
The embodiment one of single-phase grounded malfunction in grounded system of low current judgment method:
Single-phase grounded malfunction in grounded system of low current judgment method of the invention the following steps are included:
The first step extracts transient current characteristic component Wvalue。
Electricity when electric current wavelet analysis mode coefficient maximum value and ground fault occur when small current neutral grounding system is worked normally
Wavelet analysis mode coefficient maximum value is flowed as transient current characteristic component Wvalue, with the small electricity of 10KV overhead transmission line in the present embodiment
It is carried out for stream earthed system.
If wavelet function Ψ (t) is compactly support, in L2It (R) is spatially τ for translation, the wavelet transformation that scale is s
It can be defined as
For convenience of calculation, need to be moved away from dispersion for scale is peaceful.If scale S=2-j, translate τ=ks=2-j, pass through this
Sample value can guarantee the high efficiency that computer calculates, and wherein j and k respectively represents scale label and translation label.Formula (1) is just
Discrete binary wavelet transformation can be converted into.In real transform, scale is all limited, then discrete binary wavelet transformation
Approaching for arbitrary signal f (t) can be described with formula (2):
Formula (2) shows that equal arbitrary signal f (t) can be approximately decomposed into S0Space base scaling function and W0~WM-1It is empty
Between wavelet function linear combination.
The DWT analysis relationship stated between the every layer coefficients decomposed for formula (2) by formula (3) and formula (4) is true
It is fixed as follows:
Comprehensively consider frequency relation and dbN between dbN wavelets waveform and change rate feature and current break waveform
Influence of the length of resolution filter to calculating, current waveform variation characteristic when for single-phase earthing, using db5 small echo to electric current
Data carry out 3 layers of transformation, and seek transient current feature point of the 3rd layer of maximum wavelet module system numerical value as composite character vector
Amount.
H in formula (3) and formula (4)0[k] and h1Relationship between [k] are as follows:
h1[k]=(- 1)kh0[N-1-k] (5)
Wherein N is the order of Daubechies small echo.For db5 small echo, wavelet decomposition filter are as follows:
h0[k]=.0033357 .012581 ,-.0062415 ,-.077571 ,-.032245 .24229 .13843 ,-
.72431 .60383 ,-.1601 }.
H can be found out according to formula (5)1[k].Using collected current data point as the starting of decomposition coefficient
Point, by c3[k]=2-3/2F [k], so that it may calculate c one by one2[k]、c1[k]、c0[k] and d3[k]、d2[k]、d1[k]、d0
[k].Its third layer small echo mode coefficient maximum value can be from d3[k]~d0It is found out in [k].
Second step establishes singlephase earth fault and judges Fisher classifier.
For small current neutral grounding system, normal state, single-phase earthing can be divided into for 10KV overhead transmission line state
Fault case, short trouble state and power failure state.Short trouble, which can be readily identified and is reported out, to be come, and power failure can also lead to
Sensor is crossed easily to identify.It is arranged by procedure condition, these two types of states can directly be judged.Being left can
Route operating status is divided into two class of normal operating condition and singlephase earth fault state.In this manner it is possible to utilize
Fisher category theory classifies to route normal state and singlephase earth fault state.
Discriminant classification function in the Fisher classifier of foundation is y=c1x1+c2x2+c3x3+…+cpxp.By x in formula1、
x2、x3、…、xpThe matrix X of compositioniFor the vector acquired in specific small current neutral grounding system.Fisher binary classifier target is just
It is to determine discriminant classification function y=c in the case where formula (6) takes maximum condition1x1+c2x2+c3x3+…+cpxpIn by c1、c2、
c3、…、cpThe Matrix C of compositioniCoefficient, and find out critical value y0。
Third step constructs statistical vector ξ=(W of small current neutral grounding systemvalue, I, E), and according to the statistical vector of construction
Determine in discriminant classification function with Wvalue, I, E it is one-to-one, by c1、c2、c3The Matrix C of compositioniSpecific value.Wherein
WvalueThe 3rd layer of wavelet coefficient module maximum value of line current db5 wavelet transformation is represented, route one of transient characteristic quantity is characterized.I represents route
Current effective value before failure and after failure, E are represented before line fault and after failure to earth electric field virtual value.I and E characterizes route list
Steady state characteristic value after preceding and generation occurs for phase ground fault.
4th step calculates feature vector y and critical vector y0And judge whether that ground fault occurs, wherein y is according to third
The determining discriminant classification function of step is calculated, according toDetermine critical value y0, whereinBefore line fault
The average value of all feature vector y,For the average value of feature vector y all under line fault conditions, s is to unite before line fault
Vector ξ line number (with proving that matrix A line number is corresponding in example) is counted, t is statistical vector ξ line number under line fault conditions (with proof example
Middle matrix B line number is corresponding)；If y < y0, then singlephase earth fault occurs；If y >=y0, then new feature vector belongs to ungrounded failure
Situation.
It is illustrated below to use this method in Fig. 1 in order to which further clearly method of the invention is introduced
The process and result that current temporary state variation waveform is judged when ground fault occurs.Figure is calculated using the calculation method of the first step
Electric current wavelet analysis mode coefficient maximum value W when being worked normally in 1value, while it is effective to record line current before ground fault occurs
Value I and effective electric field value E obtains single-phase normal operation data as shown in Table 1, and with 1 data of matrix A record sheet.
Table 1
Similarly, electric current wavelet analysis mode coefficient is calculated in Fig. 1 when ground fault occurs most using the calculation method of the first step
Big value Wvalue, while line current virtual value I and effective electric field value E after ground fault occurs is recorded, obtain list as shown in Table 2
Data are operated normally, and mutually with 2 data of matrix B record sheet.
Table 2
For matrix A and matrix B, discriminant classification function can be found out are as follows:
Y=0.0014x1-0.1005x2+0.0059x3 (7)
In conjunction withIt can may further calculate critical value y0=2.22103.
It, can be in the hope of according to formula (7) for the ungrounded situation of matrix AFor matrix B Grounding,
It can be in the hope ofIn formulaFor the average value of feature vector y all before line fault,For line fault conditions
Under all feature vector y average value.
It can be as follows to singlephase earth fault judgment rule according to the 4th step:
If counting counted new feature vector y > y0, then new feature vector belongs to ungrounded fault condition；If meter
Counted new feature vector y < y0, then singlephase earth fault occurs.
To judge whether the Fisher classifier established in example foundation is effective, needs to discuss corresponding F distribution statistics amount,
Carry out the discussion of discriminant function confidence.If F >=Fα, then the discriminant function established is effective, if F < Fα, then discriminant function is invalid.
Statistic in this example
In α=0.005, Fα(p, s+t-p-1)=Fα(3,25)=5.46.
Thus, F > F α, therefore Fisher classifier foundation is effective.
Similarly, if B phase or C phase ground fault occur in Fig. 1, transient process will affect the electric current wavelet analysis value of A phase
Change with A phase electric field value, according to B or C ground resistance size, A phase is influenced of different sizes.Applicant simulates 200 Europe of B phase
When nurse is grounded, A phase one group of vector obtained is (300.01,14,550), carries it into formula (7), can be calculated y=
2.258014>y0, can differentiate that A phase does not have ground fault by criteria theorem, not generate wrong report.When A phase measures vector
When for (251,15,22), y=1.3337 < y0, at this moment sentence A phase and is grounded generation, it is consistent with high resistance ground experimental conditions.
It is above to differentiate that illustration is illustrated single-phase grounded malfunction in grounded system of low current judgment method of the present invention and sentences in ground fault
The successful of disconnected aspect.
The embodiment two of single-phase grounded malfunction in grounded system of low current judgment method:
The difference of embodiment two and embodiment one is only that the single-phase statistics of the small current neutral grounding system constructed in third step
Vector ξ is different, this is because in practice, data difference measured by every line current and electric field is all bigger, electric current
Transient changing is also bigger, and wavelet analysis mode coefficient maximum value is not also identical.Therefore, it is difficult to establish the single-phase of a parameter fixation
Ground fault Fisher disaggregated model is suitble to all lines branch.In order to solve this problem, it is necessary to which extensive classifier is established, and is made
Classifier has adaptive learning capacity.Classifier parameters are adaptively established and specifically include following steps.
Step 1: electric field falls statistical law when being occurred according to single-phase earthing, and line electricity field measure ground fault report is arranged
Police falls range in (n1%, n2%) section, then last entry value of composite character vector can be constructed as Emin(1-n1%), Emin
(1-n2%), Emax(1-n1%), Emax(1-n2%).Wherein electric field falls percentage and refers to that previous electric field measurement virtual value subtracts
Go current electric field value divided by previous electric field value.
Step 2: constructing four grounded fault feature vector With24 groups of electric current small echo is sampled when respectively route works normally to become
Change 3 layers of maximum coefficient value mean value and line current mean value.According to statistical result, have respectively to wavelet coefficient and current value
It is grounded the minimum limit adjustment of trend feature.In this manner it is possible to 24 groups of sampled datas and 4 groups of pre-established ground fault characteristics
According to establishing Fisher adaptive classifier.
Step 3: updating classifier index.It establishes vector of samples and saves table, record sampling markers.Regular link is sampled
Data, which are done, classifies, and general classifier is not alarmed.When there is no ground fault, if vector wrong report is ground connection by classifier,
At this moment it needs to update new vector in 24 groups, recalculates classifier parameters.In case of ground connection, but do not quote
Come.It then needs to be added to vector in ground fault feature vector, recalculates classifier parameters.Each ground fault alarm
When, record alarm vector sum markers issues from the background after progress on-site verification and updates the order of classifier index, complete Fisher
Sorting parameter updates.
Claims (2)
1. single-phase grounded malfunction in grounded system of low current judgment method, which comprises the following steps: the first step is extracted
Single-phase transient current characteristic component Wvalue, wherein WvalueFor the 3rd layer of small echo mode coefficient maximum value of line current db5 wavelet transformation,
The 3rd layer of small echo mode coefficient of line current db5 wavelet transformationC in formula3[k]=23/2f
[k], Wherein h0[k] is wavelet decomposition filter, and j and k respectively represent scale label peace
Move label；
Second step establishes singlephase earth fault and judges Fisher classifier, the discriminant classification in Fisher classifier established
Function is y=c1x1+c2x2+c3x3+…+cpxp, by x in formula1、x2、x3、…、xpThe matrix X of compositioniFor specific small current neutral grounding
The row vector acquired in system, wherein by c1、c2、c3、…、cpThe Matrix C of compositioniAccording toIt is determined when taking maximum；
Third step constructs single-phase statistical vector ξ=(W of small current neutral grounding systemvalue, I, E), and according to the statistical vector of construction
It determines in discriminant classification function by c1、c2、c3The Matrix C of compositioniSpecific value, wherein I be line fault before and failure after electricity
Flow virtual value, E is represented before line fault and after failure to earth electric field virtual value；
4th step calculates feature vector y and critical vector y0And judge whether that ground fault occurs, wherein y is determined according to third step
Discriminant classification function be calculated, according toDetermine critical value y0, whereinFor spies all before line fault
The average value of vector y is levied,For the average value of feature vector y all under line fault conditions, s be count before line fault to
ξ line number is measured, t is statistical vector ξ line number under line fault conditions；If y < y0, then singlephase earth fault occurs；If y >=y0, then newly
Feature vector belongs to ungrounded fault condition.
2. single-phase grounded malfunction in grounded system of low current judgment method according to claim 1, it is characterised in that: described
In the single-phase statistical vector ξ constructed in third step, it is added Total 4 groups of pre-established ground fault data are adaptive to establish the Fisher
Classifier, (n in formula1%, n2%) fall range for the alarm of line electricity field measure ground fault.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811582682.6A CN109375041B (en) | 2018-12-24 | 2018-12-24 | Single-phase grounding fault judgment method for small-current grounding system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811582682.6A CN109375041B (en) | 2018-12-24 | 2018-12-24 | Single-phase grounding fault judgment method for small-current grounding system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109375041A true CN109375041A (en) | 2019-02-22 |
| CN109375041B CN109375041B (en) | 2021-01-05 |
Family
ID=65371566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811582682.6A Active CN109375041B (en) | 2018-12-24 | 2018-12-24 | Single-phase grounding fault judgment method for small-current grounding system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109375041B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112114232A (en) * | 2020-09-22 | 2020-12-22 | 福州大学 | Monopole earth fault distance measuring method based on wavelet decomposition and DBN |
| CN113820621A (en) * | 2021-08-30 | 2021-12-21 | 安徽莱特实业集团有限公司 | Single-phase earth fault analysis method based on transient characteristic fault indicator state transition |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010060329A (en) * | 2008-09-01 | 2010-03-18 | Patokkusu Japan Kk | Apparatus and method for measuring leakage current of electrical path and electric instrument |
| CN106199342A (en) * | 2016-09-20 | 2016-12-07 | 西安科技大学 | A kind of wire selection method for power distribution network single phase earthing failure |
| CN107340459A (en) * | 2016-11-24 | 2017-11-10 | 安徽江淮汽车集团股份有限公司 | A kind of DC Line Fault arc method for measuring and system |
| CN107451557A (en) * | 2017-07-29 | 2017-12-08 | 吉林化工学院 | Transmission line short-circuit fault diagnostic method based on experience wavelet transformation and local energy |
| CN108646149A (en) * | 2018-04-28 | 2018-10-12 | 国网江苏省电力有限公司苏州供电分公司 | Fault electric arc recognition methods based on current characteristic extraction |
| CN110596533A (en) * | 2019-09-12 | 2019-12-20 | 山东大学 | Power distribution network single-phase earth fault section positioning method and system |
-
2018
- 2018-12-24 CN CN201811582682.6A patent/CN109375041B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010060329A (en) * | 2008-09-01 | 2010-03-18 | Patokkusu Japan Kk | Apparatus and method for measuring leakage current of electrical path and electric instrument |
| CN106199342A (en) * | 2016-09-20 | 2016-12-07 | 西安科技大学 | A kind of wire selection method for power distribution network single phase earthing failure |
| CN107340459A (en) * | 2016-11-24 | 2017-11-10 | 安徽江淮汽车集团股份有限公司 | A kind of DC Line Fault arc method for measuring and system |
| CN107451557A (en) * | 2017-07-29 | 2017-12-08 | 吉林化工学院 | Transmission line short-circuit fault diagnostic method based on experience wavelet transformation and local energy |
| CN108646149A (en) * | 2018-04-28 | 2018-10-12 | 国网江苏省电力有限公司苏州供电分公司 | Fault electric arc recognition methods based on current characteristic extraction |
| CN110596533A (en) * | 2019-09-12 | 2019-12-20 | 山东大学 | Power distribution network single-phase earth fault section positioning method and system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112114232A (en) * | 2020-09-22 | 2020-12-22 | 福州大学 | Monopole earth fault distance measuring method based on wavelet decomposition and DBN |
| CN113820621A (en) * | 2021-08-30 | 2021-12-21 | 安徽莱特实业集团有限公司 | Single-phase earth fault analysis method based on transient characteristic fault indicator state transition |
| CN113820621B (en) * | 2021-08-30 | 2023-11-17 | 安徽莱特实业集团有限公司 | Transient characteristic fault indicator state transition-based single-phase earth fault analysis method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109375041B (en) | 2021-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105425118B (en) | A kind of Multi-information acquisition fault arc detection method and device | |
| CN110082640B (en) | Distribution network single-phase earth fault identification method based on long-time memory network | |
| Bíscaro et al. | Integrated fault location and power-quality analysis in electric power distribution systems | |
| CN105512474B (en) | A kind of method for detecting abnormality of Transformer's Condition Monitoring data | |
| Li et al. | A generic waveform abnormality detection method for utility equipment condition monitoring | |
| CN106199305A (en) | Underground coal mine electric power system dry-type transformer insulation health state evaluation method | |
| CN105425076A (en) | Method of carrying out transformer fault identification based on BP neural network algorithm | |
| CN106324321A (en) | Monitoring method and monitoring device for resistive current of zinc oxide lightning arrester | |
| CN104215669B (en) | The moisture measurement method of transformer insulating system | |
| CN110133438A (en) | A kind of singlephase earth fault discrimination method based on phase space reconfiguration Yu conductance feature | |
| CN112505484B (en) | Medium-voltage distribution cable latent fault identification method for small-resistance grounding system | |
| CN109375041A (en) | Single-phase grounded malfunction in grounded system of low current judgment method | |
| CN109188197A (en) | A kind of assessment system and method for high-tension cable health index | |
| CN108344922A (en) | A kind of transmission line of electricity direct lightning strike fault recognition method based on similar differentiation and S-transformation | |
| CN109443190A (en) | Transient traveling wave-based transformer winding deformation online monitoring method and device | |
| CN114580829A (en) | Power utilization safety sensing method, equipment and medium based on random forest algorithm | |
| CN111999591B (en) | Method for identifying abnormal state of primary equipment of power distribution network | |
| CN106980051B (en) | A kind of intermittence tandem type fault electric arc recognition methods | |
| CN106159940B (en) | The optimal points distributing methods of PMU based on network load specificity analysis | |
| CN106646138B (en) | Distribution net work earthing fault localization method based on the conversion of more sample frequency wavelet character energy | |
| CN105353236A (en) | On-line remote detection method and device for detecting state of disc-type insulator | |
| Wu et al. | Transmission line fault cause identification method based on transient waveform image and MCNN-LSTM | |
| CN105675475B (en) | A kind of ground net corrosion speed grade prediction technique | |
| CN111614083B (en) | Big data analysis method suitable for 400V power supply network topology identification | |
| EP4005047B1 (en) | Anomaly detection in energy systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |