CN104777410A - Partial discharge pattern identification method for crosslinked polyethylene cable - Google Patents
Partial discharge pattern identification method for crosslinked polyethylene cable Download PDFInfo
- Publication number
- CN104777410A CN104777410A CN201510191809.1A CN201510191809A CN104777410A CN 104777410 A CN104777410 A CN 104777410A CN 201510191809 A CN201510191809 A CN 201510191809A CN 104777410 A CN104777410 A CN 104777410A
- Authority
- CN
- China
- Prior art keywords
- partial discharge
- cable
- matrix
- power cable
- imf
- 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
Abstract
The invention discloses a partial discharge pattern identification method for a crosslinked polyethylene cable, and belongs to the technical field of online monitoring and fault diagnosis of electrical equipment. The partial discharge pattern identification method comprises the following steps: adopting online or offline monitoring data of a cable, performing partial discharge signal feature extraction based on the natural mode singular value decomposition technology, and selecting the sample data to realizing learning of a cable partial discharge detection limit learning machine model, so as to realize partial discharge detection of the XLPE (Crosslinked Polyethylene) power cable. The partial discharge pattern identification method disclosed by the invention aims to running state of seven cables, based on the natural mode singular value decomposition technology, performs feature extraction on the corresponding raw signals corresponding to different running states of the cables, and determines the target vector form of the sample data, so as to complete partial discharge sample data set construction of the XLPE power cable, and learn and test the constructed partial discharge detection ELM model of the cable. The partial discharge pattern identification method disclosed by the invention can accurately and quickly identify the insulation defect and partial discharge mode of the power cable, so as to ensure safe and healthy operation of cable equipment, and provide the basis for the power cable repair scheme.
Description
Technical field
The invention belongs to the technical field of electrical equipment online supervision and fault diagnosis.
Background technology
Crosslinked polyethylene (Crosslinked Polyethylene, XLPE) power cable is the visual plant of electric system, guarantee its reliability service, reduce power failure maintenance times and time, realizing repair based on condition of component is the important content ensureing power grid security reliability service.Although have the power cable detection method for local discharge such as method of difference, direction coupled method, Electromagnetic coupling method, high frequency capacitance method, ultrasonic Detection Method at present, but existing methodical effect still has much room for improvement, in the urgent need to having new method innovation and application in the Partial Discharge Detection problem solving XLPE power cable.Therefore, the PD Pattern Recognition of the monitoring information of or off-line online based on power cable is significant.Can the insulation defect of Timeliness coverage power cable and shelf depreciation type, for its State Maintenance provides foundation.
Summary of the invention
The object of the invention is to adopt the Monitoring Data of the online or off-line of cable, the feature extraction of local discharge signal is carried out based on natural mode of vibration svd theory, choose the study that sample data carries out cable local discharge detection limit learning machine model, and then realize the XLPE Cable Partial Discharge mode identification method to XLPE power cable Partial Discharge Detection.
Step of the present invention is:
A, the creepage discharge defect scratching discharge defect, joint stress cone dislocation discharge defect and outer semiconducting layer incision position for bubble-discharge defect in major insulation, floating potential discharge defect, major insulation and major insulation hurt the selected shelf depreciation type of discharge defect six kinds, and six kinds of partial discharges fault running statuses and normal job category are the running status of seven kinds of cables altogether;
B, choose contain cable running status off-line or online Monitoring Data as data source;
C, theoretical based on natural mode of vibration svd, the original signal corresponding to the various different running status of the cable of step b gained carries out feature extraction;
(1) the time frequency analysis characteristic utilizing EMD good carries out adaptive decomposition to original signal, obtains the modal matrix be made up of signal IMF component;
(2) svd is carried out to modal matrix, obtain the singular value of modal matrix, as the characteristic quantity of power cable partial discharge signal;
D, determine the object vector expression way of the Partial Discharge Detection ELM model that the different running status of power cable is corresponding;
E, for kind of the running status of 7 described in step a, the raw data of step b gained is carried out screening and classifying, then carry out according to the method for step c the characteristic quantity that feature extraction obtains each sample data, determine the object vector form of each sample data according to the mode of steps d, thus complete the structure of XLPE power cable shelf depreciation sample data collection;
F, the sample data collection of step e gained is divided into training sample set and test sample book collection in the ratio of 2:1;
G, structure power cable Partial Discharge Detection ELM model; Determine the input layer number of the power cable Partial Discharge Detection model based on ELM, the number of hidden nodes, output layer nodes and activation function
;
H, training sample set based on step f gained, the carrying out cable local discharge constructed by step g being detected to ELM model learns;
I, test sample book collection based on step f gained, after the training obtain step h, cable local discharge detects ELM model and tests.
The step that above-mentioned steps c original signal of the present invention carries out feature extraction is:
A, according to cable local discharge signal
all extreme points, adopt cubic spline function simulate maximum value minimal value envelope respectively
with
, obtain the mean value of its upper and lower envelope
（1）；
B, analysis
with
difference
,
（2），
If
iMF, then
it is exactly signal
first IMF component; Otherwise, if
not IMF, then it can be used as new
, repetitive (2)
ksecondary
（3）
In formula,
with
be respectively
ksecondary and
k-1 screening the data obtained,
for the mean value of upper and lower envelope, utilize
value, usually get 0.2 ~ 0.3, judge whether each the selection result is IMF component
（4）
When
meet
value requirement, then make
（5）
for signal
first component meeting IMF condition;
C, order
（6）
?
as new
, constantly repeat above process, obtain second IMF successively
, the 3rd IMF
..., until the
nnthe surplus that rank IMF component is corresponding
for monotonic quantity or EMD decomposable process stopping when can be considered measuring error; So,
（7）
In formula,
for trend term, represent average tendency or the average of signal;
D, by original signal
all IMF component combination together, form modal matrix
a , namely
（8）；
E, to modal matrix
a carry out svd, obtain the singular value vector of modal matrix, it can be used as the proper vector of portraying power cable shelf depreciation;
（9）
In formula,
with
be respectively
rank and
rank orthogonal matrix,
it is matrix
a ?
iindividual eigenwert,
diagonal matrix, and
, its element is matrix
a non-negative singular value, and by descending sort;
it is matrix
a order,
with
be respectively
u with
v ?
irow singular value vector, the frequency of difference respective signal and temporal information.
The learning process that carries out that above-mentioned steps h cable local discharge of the present invention detects ELM model is:
A, setting input layer weights
and hidden layer threshold value
,
,
for the number of hidden nodes;
The hidden layer output matrix of b, calculation training sample set
, wherein,
;
C, calculating
moore-Penrose generalized inverse
; When
during for nonsingular matrix,
by formula
calculate, otherwise, adopt singular value decomposition method to solve;
D, calculating export weight
, wherein
.
The step that after training described in above-mentioned steps i of the present invention, cable local discharge detection ELM model carries out testing is:
A, calculate the hidden layer output matrix of corresponding test sample book data
;
The output of b, calculating power cable Partial Discharge Detection model
;
In c, the row vector that exports using ELM, electric discharge type corresponding to greatest member value is as testing result;
D, the actual shelf depreciation type of the testing result of ELM and power cable to be made comparisons, calculate rate of correct diagnosis, carried model is tested.
The present invention is directed to the different shelf depreciation patterns that XLPE power cable insulation defect causes, utilize the Monitoring Data of mounted monitoring device or system, both EMD multiscale analysis and Structured Singular Value Theory are combined, proposes a kind of XLPE cable Partial Discharge Pattern Recognition Method based on natural mode of vibration svd and ELM.This invention effectively can choose the characteristic quantity of the various shelf depreciation pattern of XLPE power cable, fully utilized the advantage that ELM generalization ability is strong, training speed is fast simultaneously, can the insulation defect of identification power cable and shelf depreciation pattern accurately and rapidly, thus ensure that the safety and Health of cable machinery runs, for the arrangement of power cable turnaround plan provides foundation.
Accompanying drawing explanation
Fig. 1 is the XLPE cable Partial Discharge Pattern Recognition Method process flow diagram based on natural mode of vibration svd and extreme learning machine;
Fig. 2 is the process flow diagram of the XLPE cable local discharge signal feature extraction based on natural mode of vibration svd;
Fig. 3 is the learning process figure of XLPE power cable Partial Discharge Detection ELM model;
Fig. 4 is the test flow chart of XLPE power cable Partial Discharge Detection ELM model.
Embodiment
Fig. 1 of the present invention is the XLPE cable Partial Discharge Pattern Recognition Method process flow diagram based on natural mode of vibration svd and extreme learning machine.Concrete steps are as follows:
Step 1: the typical shelf depreciation type of selected power cable, divides the running status of cable.For the common insulation defect discharge type of cable and feature, the shelf depreciation type choosing six kinds of typical defects is studied, that is: bubble-discharge defect in major insulation, floating potential discharge defect, major insulation scratch the creepage discharge defect of discharge defect, major insulation incised wound discharge defect, joint stress cone dislocation discharge defect and outer semiconducting layer incision position.Therefore, in the present invention, the running status of cable is divided into seven kinds, comprises normal work and above-mentioned six kinds of typical partial discharges fault running statuses.
Step 2: choose contain cable running status off-line or online Monitoring Data as data source.This data source can be obtained by off-line or on-line monitoring by cable local discharge on-Line Monitor Device.
Step 3: theoretical based on natural mode of vibration svd, the original signal corresponding to the various different running status of the cable of step 2 gained carries out feature extraction.(1) the time frequency analysis characteristic utilizing EMD good carries out adaptive decomposition to original signal, obtains the modal matrix be made up of signal IMF component; (2) svd is carried out to modal matrix, obtain the singular value of modal matrix, as the characteristic quantity of power cable partial discharge signal.
Step 4: the object vector expression way determining the Partial Discharge Detection ELM model that the different running status of power cable is corresponding.The present invention adopts the vector form of 7 dimension 0-1 to represent 7 kinds of running statuses of power cable, adopts [0,0,0,0,0,0,1] respectively
t, [0,0,0,0,0,1,0]
t, [0,0,0,0,1,0,0]
t, [0,0,0,1,0,0,0]
t, [0,0,1,0,0,0,0]
t, [0,1,0,0,0,0,0]
t[1,0,0,0,0,0,0]
trepresent that bubble-discharge defect in the normal work of power cable, major insulation, floating potential discharge defect, major insulation scratch 7 kinds of running statuses such as discharge defect, joint stress cone dislocation discharge defect, the creepage discharge defect of outer semiconducting layer incision position and major insulation incised wound discharge defect.Therefore, carry power cable Partial Discharge Detection ELM model output form be 7 dimensional vectors, and using corresponding for greatest member value in vector running status (shelf depreciation type or normally work) as testing result.
Step 5: build the sample data collection of power cable under various running status.For kind of the running status of 7 described in step 1, the raw data of step 2 gained is carried out screening and classifying, then carry out according to the method for step 3 characteristic quantity that feature extraction obtains each sample data, determine the object vector form of each sample data according to the mode of step 4, thus complete the structure of XLPE power cable shelf depreciation sample data collection.
Step 6: the sample data collection of step 5 gained is divided into training sample set and test sample book collection according to a certain percentage.In the present invention, it is roughly the same that training sample concentrates the quantity of Different categories of samples to ensure, and training sample set and test sample book collection demand fulfillment are independent and with distribution.Respectively the sample data of power cable under 7 kinds of running statuses is divided into training sample set in the ratio of about 2:1
with test sample book collection
.Wherein,
for feature vector dimension,
for the status number of cable running status,
with
be respectively the quantity of training sample set, test sample book collection.
Step 7: build power cable Partial Discharge Detection ELM model.Determine the input layer number of the power cable Partial Discharge Detection model based on ELM, the number of hidden nodes, output layer nodes and activation function
.In the present invention, input layer number is the dimension of proper vector, and output layer nodes is the running status number 7 of power cable, and the number of hidden nodes elects 2 times of the dimension of proper vector as, and excitation function selects sigmoid function:
.
Step 8: based on the training sample set of step 6 gained, the carrying out cable local discharge constructed by step 7 being detected to ELM model learns;
Step 9: based on the test sample book collection of step 6 gained, that obtain step 8, after training cable local discharge detects ELM model and tests.
Fig. 2 is the process flow diagram of the XLPE cable local discharge signal feature extraction based on natural mode of vibration svd.Cable local discharge feature extraction flow process proposed by the invention, comprises the following steps:
Step 31: according to cable local discharge signal
all extreme points, adopt cubic spline function simulate maximum value minimal value envelope respectively
with
, obtain the mean value of its upper and lower envelope
（1）
Step 32: analyze
with
difference
,
（2）
If
iMF, then
it is exactly signal
first IMF component; Otherwise, if
not IMF, then it can be used as new
, repetitive (2)
ksecondary
（3）
In formula,
with
be respectively
ksecondary and
k-1 screening the data obtained,
for the mean value of upper and lower envelope, utilize
value (usually getting 0.2 ~ 0.3) judge whether each the selection result is IMF component
（4）
When
meet
value requirement, then make
（5）
for signal
first component meeting IMF condition.
Step 33: order
（6）
?
as new
, constantly repeat above process, obtain second IMF successively
, the 3rd IMF
..., until the
nnthe surplus that rank IMF component is corresponding
for monotonic quantity or EMD decomposable process stopping when can be considered measuring error.So,
（7）
In formula,
for trend term, represent average tendency or the average of signal.
Step 34: by original signal
all IMF component combination together, form modal matrix
a , namely
（8）
Step 35: to modal matrix
a carry out svd, obtain the singular value vector of modal matrix, it can be used as the proper vector of portraying power cable shelf depreciation.
（9）
In formula,
with
be respectively
rank and
rank orthogonal matrix,
it is matrix
a ?
iindividual eigenwert,
diagonal matrix, and
, its element is matrix
a non-negative singular value, and by descending sort;
it is matrix
a order,
with
be respectively
u with
v ?
irow singular value vector, the frequency of difference respective signal and temporal information.
Fig. 3 is the learning process figure of XLPE power cable Partial Discharge Detection ELM model.The present invention carry the learning process of model, specifically comprise the following steps:
Step 81: random setting input layer weights
and hidden layer threshold value
,
,
for the number of hidden nodes;
Step 82: the hidden layer output matrix of calculation training sample set
, wherein,
；
Step 83: calculate
moore-Penrose generalized inverse
.When
during for nonsingular matrix,
by formula
calculate, otherwise, adopt singular value decomposition method to solve;
Step 84: calculate and export weight
, wherein
;
Fig. 4 is the test flow chart of XLPE power cable Partial Discharge Detection ELM model.The present invention carry the testing process of model, comprise the following steps:
Step 91: the hidden layer output matrix calculating corresponding test sample book data
;
Step 92: the output calculating power cable Partial Discharge Detection model
;
Step 93: the electric discharge type that greatest member value is corresponding in the row vector that ELM exports is as testing result;
Step 94: the actual shelf depreciation type of the testing result of ELM and power cable made comparisons, calculates rate of correct diagnosis, tests carried model.
Claims (4)
1. an XLPE Cable Partial Discharge mode identification method, is characterized in that: the steps include:
A, the creepage discharge defect scratching discharge defect, joint stress cone dislocation discharge defect and outer semiconducting layer incision position for bubble-discharge defect in major insulation, floating potential discharge defect, major insulation and major insulation hurt the selected shelf depreciation type of discharge defect six kinds, and six kinds of partial discharges fault running statuses and normal job category are the running status of seven kinds of cables altogether;
B, choose contain cable running status off-line or online Monitoring Data as data source;
C, theoretical based on natural mode of vibration svd, the original signal corresponding to the various different running status of the cable of step b gained carries out feature extraction;
(1) the time frequency analysis characteristic utilizing EMD good carries out adaptive decomposition to original signal, obtains the modal matrix be made up of signal IMF component;
(2) svd is carried out to modal matrix, obtain the singular value of modal matrix, as the characteristic quantity of power cable partial discharge signal;
D, determine the object vector expression way of the Partial Discharge Detection ELM model that the different running status of power cable is corresponding;
E, for kind of the running status of 7 described in step a, the raw data of step b gained is carried out screening and classifying, then carry out according to the method for step c the characteristic quantity that feature extraction obtains each sample data, determine the object vector form of each sample data according to the mode of steps d, thus complete the structure of XLPE power cable shelf depreciation sample data collection;
F, the sample data collection of step e gained is divided into training sample set and test sample book collection in the ratio of 2:1;
G, structure power cable Partial Discharge Detection ELM model; Determine the input layer number of the power cable Partial Discharge Detection model based on ELM, the number of hidden nodes, output layer nodes and activation function
;
H, training sample set based on step f gained, the carrying out cable local discharge constructed by step g being detected to ELM model learns;
I, test sample book collection based on step f gained, after the training obtain step h, cable local discharge detects ELM model and tests.
2. XLPE Cable Partial Discharge mode identification method according to claim 1, is characterized in that: the extraction step of step c is:
A, according to cable local discharge signal
all extreme points, adopt cubic spline function simulate maximum value minimal value envelope respectively
with
, obtain the mean value of its upper and lower envelope
（1）；
B, analysis
with
difference
,
（2），
If
iMF, then
it is exactly signal
first IMF component; Otherwise, if
not IMF, then it can be used as new
, repetitive (2)
ksecondary
（3）
In formula,
with
be respectively
ksecondary and
k-1 screening the data obtained,
for the mean value of upper and lower envelope, utilize
value, usually get 0.2 ~ 0.3, judge whether each the selection result is IMF component
（4）
When
meet
value requirement, then make
（5）
for signal
first component meeting IMF condition;
C, order
（6）
?
as new
, constantly repeat above process, obtain second IMF successively
, the 3rd IMF
..., until the
nnthe surplus that rank IMF component is corresponding
for monotonic quantity or EMD decomposable process stopping when can be considered measuring error; So,
（7）
In formula,
for trend term, represent average tendency or the average of signal;
D, by original signal
all IMF component combination together, form modal matrix
a , namely
（8）；
E, to modal matrix
a carry out svd, obtain the singular value vector of modal matrix, it can be used as the proper vector of portraying power cable shelf depreciation;
（9）
In formula,
with
be respectively
rank and
rank orthogonal matrix,
it is matrix
a ?
iindividual eigenwert,
diagonal matrix, and
, its element is matrix
a non-negative singular value, and by descending sort;
it is matrix
a order,
with
be respectively
u with
v ?
irow singular value vector, the frequency of difference respective signal and temporal information.
3. XLPE Cable Partial Discharge mode identification method according to claim 1, is characterized in that: the learning process of step h is:
A, setting input layer weights
and hidden layer threshold value
,
,
for the number of hidden nodes;
The hidden layer output matrix of b, calculation training sample set
, wherein,
;
C, calculating
moore-Penrose generalized inverse
; When
during for nonsingular matrix,
by formula
calculate, otherwise, adopt singular value decomposition method to solve;
D, calculating export weight
, wherein
.
4. XLPE Cable Partial Discharge mode identification method according to claim 1, is characterized in that: the testing procedure of step I is:
A, calculate the hidden layer output matrix of corresponding test sample book data
;
The output of b, calculating power cable Partial Discharge Detection model
;
In c, the row vector that exports using ELM, electric discharge type corresponding to greatest member value is as testing result;
D, the actual shelf depreciation type of the testing result of ELM and power cable to be made comparisons, calculate rate of correct diagnosis, carried model is tested.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510191809.1A CN104777410A (en) | 2015-04-22 | 2015-04-22 | Partial discharge pattern identification method for crosslinked polyethylene cable |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510191809.1A CN104777410A (en) | 2015-04-22 | 2015-04-22 | Partial discharge pattern identification method for crosslinked polyethylene cable |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104777410A true CN104777410A (en) | 2015-07-15 |
Family
ID=53618995
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510191809.1A Pending CN104777410A (en) | 2015-04-22 | 2015-04-22 | Partial discharge pattern identification method for crosslinked polyethylene cable |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104777410A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105717422A (en) * | 2015-12-04 | 2016-06-29 | 国家电网公司 | High-voltage power equipment partial discharge feature extraction method and apparatus |
| CN106503612A (en) * | 2016-09-12 | 2017-03-15 | 国网浙江省电力公司舟山供电公司 | Direct current cables local discharge signal mode identification method and system based on compressive sensing theory |
| CN106546886A (en) * | 2016-11-03 | 2017-03-29 | 云南电网有限责任公司普洱供电局 | A kind of cable wave of oscillation Partial discharge signal feature extracting method |
| CN106569099A (en) * | 2016-10-10 | 2017-04-19 | 江苏省电力公司泰州供电公司 | Method for compressing partial discharge ultrahigh-frequency signals based on singular value decomposition |
| CN106874836A (en) * | 2016-12-29 | 2017-06-20 | 国网山东省电力公司菏泽供电公司 | A kind of cable connector running rate recognizing method based on Infrared Thermogram |
| CN107037327A (en) * | 2016-10-09 | 2017-08-11 | 中国电力科学研究院 | Partial discharges fault judges feature extracting method and decision method |
| CN107422235A (en) * | 2017-08-30 | 2017-12-01 | 广东电网有限责任公司珠海供电局 | A kind of cable local discharge Signal Pre-Processing Method |
| CN107561420A (en) * | 2017-08-30 | 2018-01-09 | 广东电网有限责任公司珠海供电局 | A kind of cable local discharge signal characteristic vector extracting method based on empirical mode decomposition |
| CN108020759A (en) * | 2016-11-03 | 2018-05-11 | 云南电网有限责任公司普洱供电局 | A kind of XLPE cable wave of oscillation fault recognition method based on PSOGSA neutral nets |
| CN109596955A (en) * | 2018-12-30 | 2019-04-09 | 国网北京市电力公司 | Shelf depreciation state determines method and device |
| CN109685138A (en) * | 2018-12-25 | 2019-04-26 | 东南大学 | A kind of XLPE power cable shelf depreciation kind identification method |
| CN109683066A (en) * | 2018-11-08 | 2019-04-26 | 山东康威通信技术股份有限公司 | Power cable typical defect local discharge signal recognition methods |
| CN110275084A (en) * | 2019-06-13 | 2019-09-24 | 中国海洋石油集团有限公司 | A kind of characteristic recognition method for umbilical cables leakage failure |
| CN111579939A (en) * | 2020-04-23 | 2020-08-25 | 天津大学 | Method for detecting partial discharge phenomenon of high-voltage power cable based on deep learning |
| CN112147465A (en) * | 2020-08-13 | 2020-12-29 | 国网浙江省电力有限公司电力科学研究院 | GIS partial discharge optical diagnosis method based on multi-fractal and extreme learning machine |
| CN115598470A (en) * | 2022-09-05 | 2023-01-13 | 国网江苏省电力有限公司无锡供电分公司（Cn） | Arc active early warning method and system based on multispectral frequency band |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102252748A (en) * | 2011-04-08 | 2011-11-23 | 东南大学 | Cavitation noise modulation feature extraction method based on empirical mode |
| CN102944769A (en) * | 2012-10-18 | 2013-02-27 | 上海市电力公司 | Fault diagnosis method of power transformer based on extreme learning machine |
| CN103077402A (en) * | 2012-12-28 | 2013-05-01 | 湖北省电力公司电力科学研究院 | Transformer partial-discharging mode recognition method based on singular value decomposition algorithm |
| CN104408302A (en) * | 2014-11-19 | 2015-03-11 | 北京航空航天大学 | Bearing variable-condition fault diagnosis method based on LMD-SVD (Local Mean Decomposition-Singular Value Decomposition) and extreme learning machine |
-
2015
- 2015-04-22 CN CN201510191809.1A patent/CN104777410A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102252748A (en) * | 2011-04-08 | 2011-11-23 | 东南大学 | Cavitation noise modulation feature extraction method based on empirical mode |
| CN102944769A (en) * | 2012-10-18 | 2013-02-27 | 上海市电力公司 | Fault diagnosis method of power transformer based on extreme learning machine |
| CN103077402A (en) * | 2012-12-28 | 2013-05-01 | 湖北省电力公司电力科学研究院 | Transformer partial-discharging mode recognition method based on singular value decomposition algorithm |
| CN104408302A (en) * | 2014-11-19 | 2015-03-11 | 北京航空航天大学 | Bearing variable-condition fault diagnosis method based on LMD-SVD (Local Mean Decomposition-Singular Value Decomposition) and extreme learning machine |
Non-Patent Citations (3)
| Title |
|---|
| 唐庆华: "XLPE高压电力电缆局部放电检测方法研究", 《XLPE高压电力电缆局部放电检测方法研究》 * |
| 孙博: "电力变压器局部放电信号去噪及特征量提取方法研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
| 苑津莎等: "基于极限学习机的变压器故障诊断方法研究", 《电测与仪表》 * |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105717422A (en) * | 2015-12-04 | 2016-06-29 | 国家电网公司 | High-voltage power equipment partial discharge feature extraction method and apparatus |
| CN105717422B (en) * | 2015-12-04 | 2018-08-10 | 国家电网公司 | A kind of high-tension electricity apparatus local discharge feature extracting method and device |
| CN106503612A (en) * | 2016-09-12 | 2017-03-15 | 国网浙江省电力公司舟山供电公司 | Direct current cables local discharge signal mode identification method and system based on compressive sensing theory |
| CN107037327A (en) * | 2016-10-09 | 2017-08-11 | 中国电力科学研究院 | Partial discharges fault judges feature extracting method and decision method |
| CN106569099A (en) * | 2016-10-10 | 2017-04-19 | 江苏省电力公司泰州供电公司 | Method for compressing partial discharge ultrahigh-frequency signals based on singular value decomposition |
| CN108020759A (en) * | 2016-11-03 | 2018-05-11 | 云南电网有限责任公司普洱供电局 | A kind of XLPE cable wave of oscillation fault recognition method based on PSOGSA neutral nets |
| CN106546886B (en) * | 2016-11-03 | 2018-06-15 | 云南电网有限责任公司普洱供电局 | A kind of cable oscillation wave Partial discharge signal feature extracting method |
| CN106546886A (en) * | 2016-11-03 | 2017-03-29 | 云南电网有限责任公司普洱供电局 | A kind of cable wave of oscillation Partial discharge signal feature extracting method |
| CN106874836A (en) * | 2016-12-29 | 2017-06-20 | 国网山东省电力公司菏泽供电公司 | A kind of cable connector running rate recognizing method based on Infrared Thermogram |
| CN107422235A (en) * | 2017-08-30 | 2017-12-01 | 广东电网有限责任公司珠海供电局 | A kind of cable local discharge Signal Pre-Processing Method |
| CN107561420A (en) * | 2017-08-30 | 2018-01-09 | 广东电网有限责任公司珠海供电局 | A kind of cable local discharge signal characteristic vector extracting method based on empirical mode decomposition |
| CN109683066A (en) * | 2018-11-08 | 2019-04-26 | 山东康威通信技术股份有限公司 | Power cable typical defect local discharge signal recognition methods |
| CN109685138A (en) * | 2018-12-25 | 2019-04-26 | 东南大学 | A kind of XLPE power cable shelf depreciation kind identification method |
| CN109685138B (en) * | 2018-12-25 | 2023-04-07 | 东南大学 | XLPE power cable partial discharge type identification method |
| CN109596955A (en) * | 2018-12-30 | 2019-04-09 | 国网北京市电力公司 | Shelf depreciation state determines method and device |
| CN109596955B (en) * | 2018-12-30 | 2021-06-22 | 国网北京市电力公司 | Partial discharge state determination method and device |
| CN110275084A (en) * | 2019-06-13 | 2019-09-24 | 中国海洋石油集团有限公司 | A kind of characteristic recognition method for umbilical cables leakage failure |
| CN110275084B (en) * | 2019-06-13 | 2021-08-10 | 中国海洋石油集团有限公司 | Characteristic identification method for leakage fault of umbilical cable |
| CN111579939A (en) * | 2020-04-23 | 2020-08-25 | 天津大学 | Method for detecting partial discharge phenomenon of high-voltage power cable based on deep learning |
| CN112147465A (en) * | 2020-08-13 | 2020-12-29 | 国网浙江省电力有限公司电力科学研究院 | GIS partial discharge optical diagnosis method based on multi-fractal and extreme learning machine |
| CN112147465B (en) * | 2020-08-13 | 2022-06-03 | 国网浙江省电力有限公司电力科学研究院 | GIS partial discharge optical diagnosis method based on multi-fractal and extreme learning machine |
| CN115598470A (en) * | 2022-09-05 | 2023-01-13 | 国网江苏省电力有限公司无锡供电分公司（Cn） | Arc active early warning method and system based on multispectral frequency band |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104777410A (en) | Partial discharge pattern identification method for crosslinked polyethylene cable | |
| CN110829417B (en) | Electric power system transient stability prediction method based on LSTM double-structure model | |
| Gilanifar et al. | Multi-task logistic low-ranked dirty model for fault detection in power distribution system | |
| CN105631771A (en) | Variable weight function-based multi-parameter cable state evaluation method | |
| CN104218570A (en) | Method and system for online evaluating overall measuring errors of electric energy measuring device | |
| CN112051481A (en) | Alternating current-direct current hybrid power grid fault area diagnosis method and system based on LSTM | |
| CN106443326A (en) | Test system and method for fault locator of power distribution network | |
| CN105467971A (en) | Electric power secondary equipment monitoring system and method | |
| CN105425768A (en) | Electric power secondary equipment monitoring device and method | |
| Guo et al. | The effect of quality and availability of measurement signals on accuracy of on-line prediction of transient stability using decision tree method | |
| CN111062569A (en) | Low-current fault discrimination method based on BP neural network | |
| Coban et al. | Artificial neural network based fault location on 230 kv transmission line using voltage and current signals | |
| Bindi et al. | Smart monitoring and fault diagnosis of joints in high voltage electrical transmission lines | |
| CN104049159A (en) | Fault detection method and device of inverter | |
| Ogboh et al. | Investigation of faults on the Nigerian power system transmission line using artificial neural network | |
| Wolkiewicz et al. | Incipient stator fault detector based on neural networks end symmetrical components analysis for induction motor drives | |
| CN105741184A (en) | Transformer state evaluation method and apparatus | |
| Ogar et al. | The use of artificial neural network for low latency of fault detection and localisation in transmission line | |
| Morsalin et al. | Induction motor inter-turn fault detection using heuristic noninvasive approach by artificial neural network with Levenberg Marquardt algorithm | |
| Koley et al. | Artificial neural network based protection scheme for one conductor open faults in six phase transmission line | |
| Zarei et al. | Broken rotor bars detection via Park's vector approach based on ANFIS | |
| CN105699043B (en) | A kind of wind tunnel sensors that improve measure stability and the method for precision | |
| CN115906350A (en) | Micro-grid fault positioning and diagnosing method | |
| Asbery et al. | Electric transmission system fault identification using artificial neural networks | |
| Didden et al. | How to connect a voltage sag-measuring device: Phase to phase or phase to neutral? |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150715 |
|
| WD01 | Invention patent application deemed withdrawn after publication |