CN111476093A - Cable terminal partial discharge mode identification method and system - Google Patents
Cable terminal partial discharge mode identification method and system Download PDFInfo
- Publication number
- CN111476093A CN111476093A CN202010149539.9A CN202010149539A CN111476093A CN 111476093 A CN111476093 A CN 111476093A CN 202010149539 A CN202010149539 A CN 202010149539A CN 111476093 A CN111476093 A CN 111476093A
- Authority
- CN
- China
- Prior art keywords
- partial discharge
- discharge
- algorithm
- polar coordinate
- lbp
- 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
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 239000013598 vector Substances 0.000 claims abstract description 18
- 230000009466 transformation Effects 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000003909 pattern recognition Methods 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012567 pattern recognition method Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000009413 insulation Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000010363 phase shift Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- 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
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
- G01R31/1263—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation
- G01R31/1272—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation of cable, line or wire insulation, e.g. using partial discharge measurements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/467—Encoded features or binary features, e.g. local binary patterns [LBP]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Testing Relating To Insulation (AREA)
Abstract
A method for recognizing the local discharge mode of cable terminal includes such steps as pretreating the local discharge signal, coordinate transformation, extracting the discharge map by L BP algorithm, training the mode recognition algorithm by the extracted characteristic vector of local discharge, inputting the data to be tested to the trained mode recognition algorithm, and recognizing.
Description
Technical Field
The invention relates to a method and a system for identifying a local discharge mode of a cable terminal, belonging to the technical field of power cables.
Background
Compared with the traditional overhead line, the power cable has the advantages of no influence of external environment, land saving, good electrical performance and the like. With the development of urban power grids, the utilization rate of power cables is continuously improved, and the reliability of cable operation is concerned by power departments.
When the cable has insulation defects, partial discharge often occurs. The partial discharge phenomenon refers to a phenomenon in which a discharge occurs in a partial region of an insulating medium, but the discharge does not penetrate between conductors to which a voltage is applied. The partial discharge contains a large amount of insulation defect information, and the type of insulation defect causing the partial discharge can be determined by performing pattern recognition on the partial discharge signal.
In the current research of partial discharge mode identification, a main flow identification method needs to generate a discharge map through reference of a power frequency phase to identify a mode, and sampling of a partial discharge signal is triggered through a power frequency reference signal. However, in field application, for a three-phase cable terminal, the power frequency reference phase is difficult to obtain, and the traditional pattern recognition scheme cannot be applied to distinguish the partial discharge types. The partial discharge signal distribution of the cable terminal under the action of three-phase voltage is complex, and it is difficult to determine which of the A, B, C three phases is adopted as a power frequency reference phase. At the present stage, a maintenance power supply of the ring main unit is adopted to obtain a power frequency phase, although the method provides a stable trigger source for collecting partial discharge data, the 0-degree position of the signal is not necessarily the 0-degree position of the working voltage of the cable, so that the collected partial discharge signal generates a phase shift, the collected discharge waveform cannot accurately correspond to the phase, and the mode identification cannot be carried out.
In the field application of the existing partial discharge mode identification method to the partial discharge mode identification of the cable terminal, the partial discharge mode identification is difficult to develop due to the fact that the phase is difficult to extract or the phase is inaccurate to extract.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides a method and a system for identifying a local discharge mode of a cable terminal, which do not need to acquire a power frequency reference phase in the field application of identifying the mode of the cable terminal and can realize the distinguishing of local discharge types.
The technical scheme of the invention is realized as follows,
a cable terminal partial discharge mode recognition method includes the steps of preprocessing collected partial discharge signals, carrying out coordinate transformation on the preprocessed partial discharge signals, taking a discharge signal polar coordinate graph as a feature graph, carrying out feature extraction on the discharge graph under a polar coordinate by adopting a rotation invariant L BP algorithm, training a mode recognition algorithm by using extracted partial discharge feature vectors, and inputting data to be tested into the trained mode recognition algorithm for recognition.
The partial discharge signal includes three types of pin plate discharge, creeping discharge, and internal discharge.
The pretreatment comprises the filtering and normalization treatment of the local discharge signal; the filtering adopts a wavelet threshold filtering method to filter the partial discharge signal; the normalization processing adopts a most value normalization method, and the conversion function of the most value normalization method is as follows:
wherein x' is normalized data; x is original data; x is the number ofmaxIs the maximum value of the original data set; x is the number ofminIs originalThe minimum value of the data set.
The coordinate transformation is to map positive partial discharge signals in the preprocessed partial discharge signals into a polar coordinate system point by point, and the initial sampling time angle is determined as the 0-degree position in the polar coordinate system in the mapping process; the sampling end time corresponds to the position of 360 degrees in the polar coordinate, so that the 20ms partial discharge signals are connected end to end in the polar coordinate graph.
The features extracted by the rotation-invariant L BP algorithm do not change due to the rotation of the map, and the rotation-invariant L BP algorithm is expressed by a mathematical expression as:
whereingcIs a central pixel point, gpFor a neighborhood pixel, ROR (X, i) represents moving the P-bit number X i times in the clock direction;
the above equation for an image pixel is to rotate the neighborhood set many times in the clock direction until the L BP is formed under the current rotationP,RThe value is minimal.
The rotation invariant L BP algorithm has 36 rotation invariant elements, the histograms of the rotation invariant elements in polar coordinate graphs of different discharge types are counted, the statistical histogram is used as the characteristic vectors of different discharge types, and the 36-dimensional discharge characteristic vector obtained by each discharge graph is VLBP=[LBP1,LBP2,…,LBP36]Wherein L BP1Is a VLBPMiddle first dimension feature quantity, L BP2Is a VLBPMiddle 2 d feature quantity, L BP36Is a VLBPThe feature quantity of the medium 36 th dimension, and the value of the L BP statistical histogram is not changed by the rotation of the discharge map.
The pattern recognition algorithm comprises a neural network algorithm and a support vector machine algorithm.
A system of a cable termination partial discharge pattern recognition method, which is a computer device including a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor executes the program to implement the following steps:
(1) each known type of partial discharge signal was collected for 20ms using an AD acquisition card.
(2) And preprocessing the collected partial discharge signals.
(3) And (3) carrying out coordinate transformation on the partial discharge signals in the step (2).
(4) Taking the polar coordinate graph of the discharge signal as a feature graph, adopting a rotation invariant L BP algorithm to perform feature extraction on the discharge graph under the polar coordinate, and taking a L BP statistical histogram as a feature vector.
(5) And training a mode identification algorithm by using the extracted partial discharge characteristic vector.
(6) And inputting the data to be tested into a trained pattern recognition algorithm for recognition.
The method has the advantages that the local discharge polar coordinate is used as the pattern recognition map, the characteristic extraction is carried out on the local discharge polar coordinate map by adopting the rotation invariant L BP operator, the pattern recognition of the local discharge can be realized under the condition that the power frequency reference phase is not extracted, and the problem that the pattern recognition cannot be carried out due to the fact that the power frequency reference phase of the local discharge signal cannot be obtained at some test sites is solved.
Drawings
FIG. 1 is a flow chart of a pattern recognition method of the present invention;
FIG. 2 is a diagram illustrating an original waveform of creeping discharge in the embodiment of the present invention;
FIG. 3 is a diagram illustrating an original waveform of an internal discharge according to an embodiment of the present invention;
FIG. 4 is a graph of the original waveform of the needle plate discharge in the embodiment of the present invention;
FIG. 5 is a polar coordinate diagram of creeping discharge in an embodiment of the present invention;
FIG. 6 is an internal discharge polar map in an embodiment of the present invention;
FIG. 7 is a map of the discharge electrode coordinates of a needle plate in an embodiment of the present invention;
FIG. 8 is a graph comparing different types of discharge characteristic differences in an embodiment of the present invention;
FIG. 9 is a comparison graph of feature differences extracted before and after rotation of the same discharge type map in the embodiment of the present invention.
Detailed Description
Fig. 1 shows a flow of a cable termination partial discharge pattern recognition method according to this embodiment, which includes the following steps:
and S1, collecting partial discharge signals of known types for 20ms by using an AD acquisition card.
In this embodiment, the TMS28335 is used as a processor for AD acquisition, and three types of partial discharge signals are respectively acquired, where the sampling time is fixed 20ms, that is, the time for sampling one power frequency cycle.
Known types of discharge are, in particular, creeping discharge, internal discharge, pin plate discharge. In this embodiment, the acquired partial discharge signal is subjected to frequency reduction processing, and the partial discharge signal after the frequency reduction processing is an envelope of the original partial discharge signal. The above-mentioned frequency-reducing processing scheme adopts envelope detection technology, which is a known technical scheme and is only used as an embodiment of the present invention, and does not limit the specific application scope of the present invention. The waveforms of the raw signals of creeping discharge, internal discharge and needle plate discharge collected by the DSP are drawn in a rectangular coordinate system, as shown in FIG. 2, FIG. 3 and FIG. 4.
And S2, preprocessing the collected partial discharge signals.
The preprocessing in the step S2 includes filtering and normalizing the partial discharge signal, where the filtering uses a wavelet threshold filtering method to filter the partial discharge signal acquired in the step S1, and the normalizing uses a most-valued normalization method, where a transfer function of the most-valued normalization method is as follows:
wherein x' is normalized data; x is original data; x is the number ofmaxIs the maximum value of the original data set; x is the number ofminIs the minimum of the original data set.
And S3, performing coordinate transformation on the partial discharge signal.
In the coordinate transformation in S3, positive partial discharge signals in the partial discharge signals preprocessed in S2 are mapped into a polar coordinate system point by point, an initial sampling time angle is set as 0-degree position in the polar coordinate system in the mapping process, and a sampling end time corresponds to 360-degree position in the polar coordinate system, so that 20ms partial discharge signals are connected in an end-to-end manner in the polar coordinate system. Fig. 5, 6, and 7 show polar coordinate maps of creeping discharge, internal discharge, and pin plate discharge after coordinate conversion.
And S4, taking the polar coordinate graphs of the discharge signals of different discharge types as feature graphs, performing feature extraction on the discharge graphs under the polar coordinates by adopting a rotation invariant L BP operator, and taking the L BP statistical histogram as a feature vector.
Further, the extracted features of the rotation invariant L BP algorithm in S4 do not change due to the rotation of the map, and the rotation invariant L BP algorithm is expressed by the mathematical expression:
whereingcIs a central pixel point, gpFor a neighborhood pixel, ROR (X, i) represents shifting the P-bit number X i times in the clock direction for the image pixel, the above equation is to rotate the neighborhood set many times in the clock direction until L BP is formed under the current rotationP,RThe value is minimal.
Furthermore, the rotation invariant L BP algorithm has 36 rotation invariant elements in total, the histogram of the rotation invariant elements in the polar coordinate graph spectrum of different discharge types is counted, and the counted histogram is used as the special histogram of different discharge typesThe feature vectors are obtained by each discharge map as 36-dimensional discharge feature vectors VLBP=[LBP1,LBP2,…,LBP36]And the rotation of the discharge map does not change the value of the L BP statistical histogram.
Further, the L BP characteristic vector front 35-dimensional characteristic vector V of creeping discharge, internal discharge and needle plate discharge is subjected to surface discharge and internal dischargeLBP=[LBP1,LBP2,…,LBP36]As shown in fig. 8, it can be seen that different types of discharge characteristics have a certain degree of distinction.
Further, L BP characteristics are extracted according to the steps after the polar coordinate graph of the needle plate discharge type is rotated by a certain angle, the discharge characteristics before and after the rotation are drawn in fig. 9, and as can be seen from fig. 9, after the discharge graph is rotated by a certain angle, L BP characteristics do not change, so that the relationship between the rotation angle of the characteristics extracted by L BP and the discharge polar coordinate is not large, that is, the discharge characteristics are not influenced by the different starting times of partial discharge acquisition.
And S5, training a mode recognition algorithm by using the extracted partial discharge characteristic vector.
The pattern recognition algorithm in S5 includes: neural network algorithm, support vector machine algorithm. Specifically, in the present embodiment, the pattern recognition algorithm of step S5 adopts a BP neural network algorithm, and sets the expected outputs of the BP neural network, where the creeping discharge is (0,0,1), the internal discharge is (0,1,0), and the needle plate discharge is (1,0,0), respectively. And training the partial discharge signal characteristic vector of a known type to a BP neural network with well-set parameters.
And S6, inputting the data to be tested into a trained pattern recognition algorithm for recognition.
In this embodiment, the data to be tested is obtained according to the steps from S1 to S4, the data to be tested is input into the trained neural network, and the output value of the BP neural network is compared with the class label to obtain the local discharge signal source to be identified. Specifically, when the value of a certain output node of the BP neural network is between 0 and 1, the output value is rounded and then compared with the set expected output, so as to obtain a pattern recognition result.
The embodiment is suitable for cable terminal partial discharge mode identification, realizes the mode identification of partial discharge under the condition that a power frequency reference phase is not easily provided at a test site, and solves the problem that the mode identification cannot be carried out due to the fact that the power frequency reference phase of the partial discharge signal cannot be obtained at some test sites.
Claims (8)
1. A cable terminal partial discharge mode identification method is characterized in that the method comprises the steps of preprocessing collected partial discharge signals, carrying out coordinate transformation on the preprocessed partial discharge signals, taking a discharge signal polar coordinate graph as a characteristic graph, carrying out characteristic extraction on the discharge graph under a polar coordinate by adopting a rotation invariant L BP algorithm, training a mode identification algorithm by using extracted partial discharge characteristic vectors, and inputting data to be tested into the trained mode identification algorithm for identification.
2. The cable termination partial discharge pattern recognition method of claim 1, wherein the partial discharge signal includes three types of pin plate discharge, creeping discharge and internal discharge.
3. The method for identifying the partial discharge pattern of the cable termination, according to claim 1, wherein the preprocessing comprises filtering and normalizing the partial discharge signal; the filtering adopts a wavelet threshold filtering method to filter the partial discharge signal; the normalization processing adopts a most value normalization method, and the conversion function of the most value normalization method is as follows:
wherein x' is normalized data; x is original data; x is the number ofmaxIs the maximum value of the original data set; x is the number ofminIs the minimum of the original data set.
4. The method for identifying the partial discharge pattern of the cable termination, as claimed in claim 1, wherein the coordinate transformation is to map the positive partial discharge signal in the preprocessed partial discharge signal into a polar coordinate system point by point, and the initial sampling time angle is defined as 0 degree position in the polar coordinate system in the mapping process; the sampling end time corresponds to the position of 360 degrees in the polar coordinate, so that the 20ms partial discharge signals are connected end to end in the polar coordinate graph.
5. The method as claimed in claim 1, wherein the extracted features of the rotation invariant L BP algorithm are not changed due to the rotation of the map, and the rotation invariant L BP algorithm is expressed by the mathematical expression:
whereingcIs a central pixel point, gpFor a neighborhood pixel, ROR (X, i) represents moving the P-bit number X i times in the clock direction;
the above equation for an image pixel is to rotate the neighborhood set many times in the clock direction until the L BP is formed under the current rotationP,RThe value is minimal.
6. The method for identifying the partial discharge mode of the cable terminal according to claim 1, wherein the rotation invariant L BP algorithm has 36 rotation invariant elements in total, the histograms of the rotation invariant elements in polar coordinate spectrums of different discharge types are counted, the statistical histogram is used as the feature vectors of different discharge types, and the 36-dimensional discharge feature vector obtained by each discharge spectrum is VLBP=[LBP1,LBP2,…,LBP36]Wherein L BP1Is a VLBPMiddle first dimension feature quantity, L BP2Is a VLBPMiddle 2 d feature quantity, L BP36Is a VLBPThe feature quantity of the medium 36 th dimension, and the value of the L BP statistical histogram is not changed by the rotation of the discharge map.
7. The cable termination partial discharge pattern recognition method of claim 1, wherein the pattern recognition algorithm comprises a neural network algorithm and a support vector machine algorithm.
8. The system for implementing the method for identifying the partial discharge pattern of the cable termination according to claims 1 to 7 is a computer device, which includes a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the following steps:
(1) collecting partial discharge signals of known types for 20ms by using an AD acquisition card;
(2) preprocessing the collected partial discharge signals;
(3) carrying out coordinate transformation on the partial discharge signals in the step (2);
(4) taking the polar coordinate graph of the discharge signal as a feature graph, performing feature extraction on the discharge graph under the polar coordinate by adopting a rotation invariant L BP algorithm, and taking a L BP statistical histogram as a feature vector;
(5) training a mode recognition algorithm by using the extracted partial discharge characteristic vector;
(6) and inputting the data to be tested into a trained pattern recognition algorithm for recognition.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010149539.9A CN111476093A (en) | 2020-03-06 | 2020-03-06 | Cable terminal partial discharge mode identification method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010149539.9A CN111476093A (en) | 2020-03-06 | 2020-03-06 | Cable terminal partial discharge mode identification method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111476093A true CN111476093A (en) | 2020-07-31 |
Family
ID=71748132
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010149539.9A Pending CN111476093A (en) | 2020-03-06 | 2020-03-06 | Cable terminal partial discharge mode identification method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111476093A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112730984A (en) * | 2021-03-31 | 2021-04-30 | 国网江西省电力有限公司供电服务管理中心 | Low-voltage distribution network phase identification method based on intelligent electric meter |
CN112881879A (en) * | 2021-04-16 | 2021-06-01 | 国网黑龙江省电力有限公司大庆供电公司 | High-voltage cable terminal partial discharge mode identification method, device and equipment |
CN113625132A (en) * | 2021-08-06 | 2021-11-09 | 国网上海市电力公司 | Cable partial discharge detection method and system based on phase alignment |
CN114062873A (en) * | 2021-11-17 | 2022-02-18 | 国网陕西省电力公司电力科学研究院 | Parallel reactor insulation fault diagnosis method and device based on convolutional neural network |
CN116381429A (en) * | 2023-03-29 | 2023-07-04 | 上海莫克电子技术有限公司 | Method and system for correcting online partial discharge detection result |
CN117708760A (en) * | 2024-02-05 | 2024-03-15 | 国网江西省电力有限公司电力科学研究院 | Multi-mode fusion-based switch cabinet multi-source partial discharge mode identification method and system |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001080176A (en) * | 1999-09-17 | 2001-03-27 | Canon Inc | Data processor, image recorder, control method thereof and storage medium |
CN103729654A (en) * | 2014-01-22 | 2014-04-16 | 青岛新比特电子科技有限公司 | Image matching retrieval system on account of improving Scale Invariant Feature Transform (SIFT) algorithm |
CN104237750A (en) * | 2014-09-05 | 2014-12-24 | 中国西电电气股份有限公司 | GIS insulation defect partial discharge fault graph drawing method |
CN104849633A (en) * | 2015-05-15 | 2015-08-19 | 国家电网公司 | Switchgear partial discharge mode recognition method |
WO2016138838A1 (en) * | 2015-03-02 | 2016-09-09 | 华为技术有限公司 | Method and device for recognizing lip-reading based on projection extreme learning machine |
CN107831409A (en) * | 2017-09-22 | 2018-03-23 | 国网山东省电力公司电力科学研究院 | The method and method for detecting abnormality of superfrequency partial discharge detection TuPu method parameter extraction |
CN108761279A (en) * | 2018-03-23 | 2018-11-06 | 广东电网有限责任公司东莞供电局 | Polar coordinate grid searching method and system for positioning partial discharge source |
CN108957251A (en) * | 2018-05-18 | 2018-12-07 | 深圳供电局有限公司 | Cable joint partial discharge mode identification method |
CN109858353A (en) * | 2018-12-26 | 2019-06-07 | 东华理工大学 | Facial image feature extracting method based on mark transformation and LBP |
CN110850244A (en) * | 2019-11-11 | 2020-02-28 | 国网湖南省电力有限公司 | Local discharge defect time domain map diagnosis method, system and medium based on deep learning |
-
2020
- 2020-03-06 CN CN202010149539.9A patent/CN111476093A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001080176A (en) * | 1999-09-17 | 2001-03-27 | Canon Inc | Data processor, image recorder, control method thereof and storage medium |
CN103729654A (en) * | 2014-01-22 | 2014-04-16 | 青岛新比特电子科技有限公司 | Image matching retrieval system on account of improving Scale Invariant Feature Transform (SIFT) algorithm |
CN104237750A (en) * | 2014-09-05 | 2014-12-24 | 中国西电电气股份有限公司 | GIS insulation defect partial discharge fault graph drawing method |
WO2016138838A1 (en) * | 2015-03-02 | 2016-09-09 | 华为技术有限公司 | Method and device for recognizing lip-reading based on projection extreme learning machine |
CN104849633A (en) * | 2015-05-15 | 2015-08-19 | 国家电网公司 | Switchgear partial discharge mode recognition method |
CN107831409A (en) * | 2017-09-22 | 2018-03-23 | 国网山东省电力公司电力科学研究院 | The method and method for detecting abnormality of superfrequency partial discharge detection TuPu method parameter extraction |
CN108761279A (en) * | 2018-03-23 | 2018-11-06 | 广东电网有限责任公司东莞供电局 | Polar coordinate grid searching method and system for positioning partial discharge source |
CN108957251A (en) * | 2018-05-18 | 2018-12-07 | 深圳供电局有限公司 | Cable joint partial discharge mode identification method |
CN109858353A (en) * | 2018-12-26 | 2019-06-07 | 东华理工大学 | Facial image feature extracting method based on mark transformation and LBP |
CN110850244A (en) * | 2019-11-11 | 2020-02-28 | 国网湖南省电力有限公司 | Local discharge defect time domain map diagnosis method, system and medium based on deep learning |
Non-Patent Citations (3)
Title |
---|
孙文星等: "基于小波矩特征信息的沿面放电阶段识别方法", 《广东电力》 * |
赵磊等: "基于GLCM和LBP的局部放电灰度图像特征提取", 《电测与仪表》 * |
黄健华: "局部放电的极坐标谱图及模式识别_黄健华", 《高压电器》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112730984A (en) * | 2021-03-31 | 2021-04-30 | 国网江西省电力有限公司供电服务管理中心 | Low-voltage distribution network phase identification method based on intelligent electric meter |
CN112881879A (en) * | 2021-04-16 | 2021-06-01 | 国网黑龙江省电力有限公司大庆供电公司 | High-voltage cable terminal partial discharge mode identification method, device and equipment |
CN113625132A (en) * | 2021-08-06 | 2021-11-09 | 国网上海市电力公司 | Cable partial discharge detection method and system based on phase alignment |
CN114062873A (en) * | 2021-11-17 | 2022-02-18 | 国网陕西省电力公司电力科学研究院 | Parallel reactor insulation fault diagnosis method and device based on convolutional neural network |
CN116381429A (en) * | 2023-03-29 | 2023-07-04 | 上海莫克电子技术有限公司 | Method and system for correcting online partial discharge detection result |
CN116381429B (en) * | 2023-03-29 | 2024-03-29 | 上海莫克电子技术有限公司 | Method and system for correcting online partial discharge detection result |
CN117708760A (en) * | 2024-02-05 | 2024-03-15 | 国网江西省电力有限公司电力科学研究院 | Multi-mode fusion-based switch cabinet multi-source partial discharge mode identification method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111476093A (en) | Cable terminal partial discharge mode identification method and system | |
CN108573225B (en) | Partial discharge signal pattern recognition method and system | |
CN108957251B (en) | Cable joint partial discharge mode identification method | |
CN109871686A (en) | Rogue program recognition methods and device based on icon representation and software action consistency analysis | |
CN106548013B (en) | Utilize the voltage sag source identification method for improving incomplete S-transformation | |
CN112036450B (en) | High-voltage cable partial discharge mode identification method and system based on transfer learning | |
CN110147760A (en) | A kind of efficient electrical energy power quality disturbance image characteristics extraction and identification new method | |
CN108734691A (en) | A kind of transmission line of electricity defect image recognition methods | |
CN111220882A (en) | Method for extracting characteristic quantity of GIS optical partial discharge spectrum | |
CN109871825B (en) | Portrait identification method based on improved local two-dimensional mode | |
CN118534191A (en) | Photovoltaic power station harmonic analysis and monitoring system under new energy power grid | |
CN115690012A (en) | Detection method for wrong connection line of electric energy meter | |
CN111289251A (en) | Rolling bearing fine-grained fault identification method | |
US20220147777A1 (en) | Automatic Partial Discharge and Noise Signals Separation using Arithmetic Coding in Time Domain and Magnitude Distributions in Frequency Domain | |
CN112285494A (en) | Power cable partial discharge mode recognition analysis system | |
Fu et al. | A noise-resistant superpixel segmentation algorithm for hyperspectral images | |
CN104125050A (en) | Ultrahigh-frequency RFID (radio frequency identification) reader protocol conformance testing method | |
CN107578016B (en) | Sparse representation-based automatic residual current waveform identification method | |
CN113283371A (en) | Local discharge feature extraction and classification method based on BRISK features | |
CN110719445A (en) | Remote meter reading system and method based on image recognition | |
CN114325072B (en) | Ferromagnetic resonance overvoltage identification method and device based on gram angular field coding | |
CN115963350A (en) | Fault positioning method and device for direct-current power distribution network | |
CN115293303A (en) | High-voltage transmission line network monitoring method, system, equipment and medium | |
CN110033082B (en) | Method for identifying deep learning model in AI (Artificial intelligence) equipment | |
Li et al. | An improved adaptive threshold BRISK feature matching algorithm based on SURF |
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: 20200731 |